Machine learning Books
Taylor & Francis Inc ModelBased Machine Learning
Book SynopsisToday, machine learning is being applied to a growing variety of problems in a bewildering variety of domains. A fundamental challenge when using machine learning is connecting the abstract mathematics of a machine learning technique to a concrete, real world problem. This book tackles this challenge through model-based machine learning which focuses on understanding the assumptions encoded in a machine learning system and their corresponding impact on the behaviour of the system.The key ideas of model-based machine learning are introduced through a series of case studies involving real-world applications. Case studies play a central role because it is only in the context of applications that it makes sense to discuss modelling assumptions. Each chapter introduces one case study and works through step-by-step to solve it using a model-based approach. The aim is not just to explain machine learning methods, but also showcase how to create, debug, and evolve them to solvTable of ContentsIntroduction. How Can Machine Learning Solve my Problem? 1. A Murder Mystery 2. Assessing People’s Skills Interlude. The Machine Learning Life Cycle 3. Meeting Your Match 4. Uncluttering Your Inbox 5. Making Recommendations 6. Understanding Asthma 7. Harnessing the Crowd 8. How to Read a Model Afterword
£68.39
IGI Global Machine Learning and AI Techniques in Interactive
Book SynopsisThe healthcare industry is predominantly moving towards affordable, accessible, and quality health care. All organizations are striving to build communication compatibility among the wide range of devices that have operated independently. Recent developments in electronic devices have boosted the research in the medical imaging field. It incorporates several medical imaging techniques and achieves an important goal for health improvement all over the world. Despite the significant advances in high-resolution medical instruments, physicians cannot always obtain the full amount of information directly from the equipment outputs, and a large amount of data cannot be easily exploited without a computer. Machine Learning and AI Techniques in Interactive Medical Image Analysis discusses how clinical efficiency can be improved by investigating the different types of intelligent techniques and systems to get more reliable and accurate diagnostic conclusions. This book further introduces segmentation techniques to locate suspicious areas in medical images and increase the segmentation accuracy. Covering topics such as computer-aided detection, intelligent techniques, and machine learning, this premier reference source is a dynamic resource for IT specialists, computer scientists, diagnosticians, imaging specialists, medical professionals, hospital administrators, medical students, medical technicians, librarians, researchers, and academicians.
£319.60
IGI Global Meta-Learning Frameworks for Imaging Applications
Book Synopsis
£192.85
IGI Global Meta-Learning Frameworks for Imaging Applications
Book Synopsis
£254.60
Elsevier Science Data Mining
Book Synopsis
£54.86
Elsevier Science Machine Learning
Book Synopsis
£84.74
Institute of Physics Publishing Machine Learning For Physicists
Book Synopsis
£67.50
Institute of Physics Publishing Mastering Computer Vision with PyTorch and
Book Synopsis
£71.25
O'Reilly Media AI Value Creators
Book Synopsis
£62.25
APress Artificial Intelligence in Medical Sciences and
Book SynopsisGet started with artificial intelligence for medical sciences and psychology. This book will help healthcare professionals and technologists solve problems using machine learning methods, computer vision, and natural language processing (NLP) techniques. The book covers ways to use neural networks to classify patients with diseases. You will know how to apply computer vision techniques and convolutional neural networks (CNNs) to segment diseases such as cancer (e.g., skin, breast, and brain cancer) and pneumonia. The hidden Markov decision making process is presented to help you identify hidden states of time-dependent data. In addition, it shows how NLP techniques are used in medical records classification. This book is suitable for experienced practitioners in varying medical specialties (neurology, virology, radiology, oncology, and more) who want to learn Python programming to help them work efficiently. It is also intended for data scientists, machine leTable of ContentsChapter 1: An Introduction to Artificial Intelligence for Medical SciencesChapter goal: This is the initial chapter. Subsequently, it encapsulates the specific context and structure of the book. Then, it states the varying medical specialties central to this book. Likewise, it properly presents independent subsets of artificial intelligence. Besides that, it unveils valuable tools for undertaking exercises; Python programming language, distribution package, and libraries. Afterward, it sufficiently acquaints you with different algorithms, including when to carry them out.Sub-topics:● Context of the book.● The book’s central point.● Artificial Intelligence subsets covered in this book.● Structure of the book.● Tools that this book implements.○ Python distribution package.○ Anaconda distribution package.○ Jupyter Notebook.○ Python libraries.● Encapsulating Artificial Intelligence.● Debunking algorithms.● Debunking supervised algorithms.● Debunking unsupervised algorithms.● Debunking Artificial Neural Networks.Chapter 2: Realizing Patterns in Common Diseases with Neural NetworksChapter goal: This chapter purportedly contains the application of artificial neural networks in modelling medical data. It properly instigates deep belief networks to model data and predicts whether a patient suffers from an ordinary disease (i.e., pneumonia and diabetes). Equally, it appraises the networks with fundamental metrics to discern the magnitude to which the networks set apart patients who suffer from the disease from those who do not.Sub-topics:● Classifying patients’ Cardiovascular disease diagnosis outcome data by executing a deepbelief network.● Preprocessing the Cardiovascular disease diagnosis outcome data.● Debunking deep belief networks.o Designing the deep belief network.o Relu Activation function.o Sigmoid activation function.● Training the deep belief network.● Outlining the deep belief networks predictions.● Considering the deep belief network’s performance.● Classifying patients’ diabetes diagnosis outcome data by executing a deep belief network.● Outlining the deep belief networks predictions .● Considering the deep belief network’s performance.● Conclusion.Chapter 3: A Case for COVID-19 Identifying Hidden States and Simulation ResultsChapter goal: This chapter instigates a set of series analysis methods to uniquely discern patterns in the US COVID-19 confirmed cases. To begin with, the Gaussian Hidden Markov Model inherits the series data, models it and identifies the hidden states, including the means and covariance in those states. Subsequently, the Monte Carlo simulation method replicates US COVID-19 confirmed cases across multiple trials, thus providing us with a rich comprehending of the patternChapter content:● Debunking the Hidden Markov Model● Descriptive analysis● Carrying Out the Gaussian Hidden Markov Modelo Considering the Hidden States in US COVID-19 Confirmed Cases with the GaussianHidden Markov Model● Simulating US COVID-19 Confirmed Cases with the Monte Carlo Simulation Methodo US COVID-19 confirmed cases simulation results● ConclusionChapter 4: Cancer Segmentation with Neural NetworksChapter goal: This chapter typically exhibits the practical application of computer vision andconvolutional neural networks for breast and skin Cancer realization and segmentation. Equally, it shows an approach to filter medical scans by applying canny, luplican, and sobel filters. It concludes by ascertaining the extent to which the networks accurately differentiate scans of patients with and without Cancer.Chapter content:● Debunking Cancer.● Debunking Skin Cancer● Depicting scans of a patient with Skin Cancer.● Classifying Patients’ Skin Cancer Diagnosis Image Data by Executing a Convolutional Neural Network.o Preprocessing the training Skin Cancer Image Data.o Preprocessing the Validation Skin Cancer Image Data.o Generating the Training Skin Cancer Diagnosis Image Data.o Tuning the Training Skin Cancer Image Data.o Executing the Convolutional Neural Network to Classify Patients’ Skin CancerDiagnosis Image Data.o Considering the Convolutional Neural Network’s Performance.o Debunking Breast Cancer.● Classifying Ultrasound Scans of Breast Cancer Patients by Executing a Convolutional Neural Network.o Preprocessing the Validation Breast Cancer Image Data .o Preprocessing the Validation Breast Cancer Image Data .o Generating the Training Breast Cancer Diagnosis Image Data.o Tuning the Training Breast Cancer Image Data.o Executing the Convolutional Neural Network to Classify Patients’ Breast CancerDiagnosis Image Data.o Considering the Convolutional Neural Network’s Performance.● Conclusion.Chapter 5: Modelling Magnetic Resonance Imaging and X-Rays by Carrying out Artificial Neural NetworksChapter goal: This chapter intimately acquaints you with the practical application of computer vision and artificial neural networks in neurology and radiology. It promptly carries out convolutional neural networks for image classification. The initial network models MRI scans to set apart patients with and without a brain tumor, and the second network models X-ray scans to set apart patients with and without pneumonia. Besides that, it unveils an effective technique for appraising networks in medical image classification.Sub-topics:● Debunking Brain Tumors.● Classifying Patients’ Model Magnetic Resonance Imaging (MRI) Data by Executing aConvolutional Neural Network.o Depicting MRI Scan of Patients with a Brain Tumor.o Depicting Brain Scans without a Brain Tumor.o Preprocessing the Training MRI Image Data.o Preprocessing the Validation MRI Image Data.o Generating the Training MRI Image Data.o Tuning the Training MRI Image Data.o Executing the Convolutional Neural Network to Classify Patients’ MRI Image Data.o Considering the Convolutional Neural Network’s Performance.● Debunking Pneumonia.o Classifying Patients’ CT scan Data by Executing a Convolutional Neural Network.o Depicting an X-Ray scan of a Patient with Pneumonia.o Depicting an X-Ray scan of a Patient without Pneumonia.o Processing the X-Ray Image Data.o Generating the Training Chest X-Ray Image Data.o Preprocessing the Validation Chest X-Ray Image Data.o Generating the Validation Chest X-Ray Image Data.o Tuning the Training Chest X-Ray Image Data.o Executing the Convolutional Neural Network to Classify Patients’ Chest X-Ray ImageData.▪ Considering the Convolutional Neural Network’s Performance.● Conclusion.Chapter 6: A Case for COVID-19 CT Scan SegmentationChapter goal: This chapter presents an approach for carrying out convolutional neural networks to model chest CT scan images and differentiate between patients with and without COVID-19.Sub-topics:● Classifying Patients’ Model Magnetic Resonance Imaging (MRI) Data by Carrying out aConvolutional Neural Network.o Depicting a Chest CT scan of a COVID-19 Negative Patient.o Depicting a CT scan of COVID-19 Negative Patient.o Preprocessing the Training COVID-19 Data.o Preprocessing the Validation COVID-19 CT Scan Data.o Generating the Training COVID-19 CT Scan Data.o Tuning the Training COVID-19 CT Scan Data.● Data.o Considering the Convolutional Neural Network’s Performance.● Conclusion.Chapter 7 Modelling Clinical Trial DataChapter goal: This chapter familiarizes you with the prime essentials of the most widespread method for adequately investigating data from a clinical trial, recognized as a survival method. It debunks the Nelson-Aalen additive model. To begin with, it encapsulates the method. Subsequently, it promptly presents exploratory analysis, then correlation analysis by carrying out the Pearson correlation method. Following that, it outlines the survival table, then fits the model. It concludes by carefully outlining the profile table, confidence interval, and reproducing the cumulative and baseline hazard.sub-topics:● Debunking Clinical Trials.● An Overview of Survival Analysis.● Context of the Chapter.● Exploring the Nelson-Aalen Additive Model.● Descriptive Analysis.● Realizing a Correlation Relationship.● Outlining the Survival Table.● Carrying out the Nelson-Aalen Additive Model.o Outlining the Nelson-Aalen additive Model’s Confidence Intervalo Discerning the Survival Hazard.o Discerning the Cumulative Survival Hazard.o Baseline Survival Hazard.● Conclusion.● References.Chapter 8: Medical Record CategorizationChapter goal: This chapter sufficiently apprises a wholesome approach for realizing patterns in medical records by carrying out a linear discriminant analysis model. To begin with, it summarizes medical recording. Subsequently, it exhibits a technique of cleansing textual data by carrying out fundamental methods like regularization and TfidfVectorizer. Afterward, it executes the method to classify the medical specialty, then it assesses the extent to which it segregates classes.Sub-topics:● Medical Records.● Context of Chapter.● Debunking Categorization with Linear Discriminant Analysis.o Descriptive Statistics.o Preprocessing the Medical Records Data.o Carrying out Regular Expression.o Carrying Out Word Vectorization.o Carrying out the Linear Discriminant Analysis Model to Classify Patients’ MedicalRecords.o Considering the Linear Discriminant Analysis Model’s Performance.● Conclusion.Chapter 9: A Case for Psychology: Factoring and Clustering Personality DimensionsChapter goal: This chapter introduces you to analyzing the underlying patterns in human behavior by promptly carrying out exploratory factor analysis and cluster analysis. To begin with, it covers the big five personality dimensions. Following that, it presents an approach for typically collecting data by retaining a Likert scale and measuring the reliability of the scale with Cronbach’s reliability testing strategy. Subsequently, it performs factor analysis; beginning with estimating Bartlett Sphericity statistics, then the Kaiser-Meyer-Olkin statistic. Following that, it rotates the eigenvalues by carrying out the varimax rotation method and estimates the proportional variances and cumulative variances. In addition, it executes the K-Means method to observe clusters in the data; beginning with standardizing the data and carrying out principal component analysis.Sub-topics:● Debunking Personality Dimensions.● Questionnaires.● Likert Scale.● Reliability.o Spearman-Brown Reliability Testing Strategy.o Carrying out Cronbach's Reliability Testing Strategy.● Carrying out Factor Model.o Carrying out the Bartlett Sphericity Test.o Carrying out the Kaiser-Meyer-Olkin Test.o Discerning K with a Scree Plot.o Carrying out Eigenvalue Rotation.▪ Varimax Rotation.● Carrying out Cluster Analysis.o Carrying out Principal Component Analysis.O Returning K-Means label.
£44.99
Cambridge University Press Machine Learning for Asset Managers
Book SynopsisSuccessful investment strategies are specific implementations of general theories. An investment strategy that lacks a theoretical justification is likely to be false. Hence, an asset manager should concentrate her efforts on developing a theory rather than on backtesting potential trading rules. The purpose of this Element is to introduce machine learning (ML) tools that can help asset managers discover economic and financial theories. ML is not a black box, and it does not necessarily overfit. ML tools complement rather than replace the classical statistical methods. Some of ML''s strengths include (1) a focus on out-of-sample predictability over variance adjudication; (2) the use of computational methods to avoid relying on (potentially unrealistic) assumptions; (3) the ability to learn complex specifications, including nonlinear, hierarchical, and noncontinuous interaction effects in a high-dimensional space; and (4) the ability to disentangle the variable search from the specificaTrade Review'The book's excellent introduction explains why machine learning techniques will benefit asset managers substantially and why traditional or classical linear techniques have limitations and are often inadequate in asset management. It makes a strong case that ML is not a black box but a set of data tools that enhance theory and improve data clarity. López de Prado focuses on seven complex problems or topics where applying new techniques developed by ML specialists will add value.' Mark S. Rzepczynski, Enterprising InvestorTable of Contents1. Introduction; 2. Denoising and detoning; 3. Distance metrics; 4. Optimal clustering; 5. Financial labels; 6. Feature importance analysis; 7. Portfolio construction; 8. Testing set overfitting.
£17.00
O'Reilly Media Learning GitHub Copilot
Book Synopsis
£44.79
Cambridge University Press Practical Smoothing
Book SynopsisThis is a practical guide to P-splines, a simple, flexible and powerful tool for smoothing. P-splines combine regression on B-splines with simple, discrete, roughness penalties. They were introduced by the authors in 1996 and have been used in many diverse applications. The regression basis makes it straightforward to handle non-normal data, like in generalized linear models. The authors demonstrate optimal smoothing, using mixed model technology and Bayesian estimation, in addition to classical tools like cross-validation and AIC, covering theory and applications with code in R. Going far beyond simple smoothing, they also show how to use P-splines for regression on signals, varying-coefficient models, quantile and expectile smoothing, and composite links for grouped data. Penalties are the crucial elements of P-splines; with proper modifications they can handle periodic and circular data as well as shape constraints. Combining penalties with tensor products of B-splines extends theseTrade Review'The title says it all. This is a practical book which shows how P-splines are used in an astonishingly wide range of settings. If you use P-splines already the book is indispensable; if you don't, then reading it will convince you it's time to start. Every example comes with an R-program available on the book's web-site, an important feature for the experienced user and novice alike.' Iain Currie, Heriot-Watt University'This book is an enlightening and at the same time extremely enjoyable read. It will serve the applied statistician who is looking for practical solutions but also the connoisseur in search of elegant concepts. The accompanying website offers reproducible code and invites to promptly enter the fascinating universe of P-splines.' Jutta Gampe, Max Planck Institute for Demographic Research'Everything you always wanted to know about P-splines, from the inventors themselves. Paul H.C. Eilers and Brian D. Marx make a compelling case for their claim that P-splines are the best practical smoother out there, providing intuition, methodology, applications, and R code that clearly demonstrate the power, flexibility, and wide applicability of this approach to smoothing.' Jeffrey Simonoff, New York University'This is the book that everyone working on smoothing models should keep handy. At last we have a manuscript that shows the real power of P-splines, their versatility, and the different perspectives you can take to use them. Chapters 1 to 3 will certainly appeal to those who want to start working in this field, and to researchers that need to deepen their knowledge of this technique. Scientists and practitioners from other areas will find chapters 4 to 8 very useful for the wide range of examples and applications. The companion package and the fact that all results (even figures) are reproducible is a real bonus. Thank you Paul and Brian for being truthful to your motto: 'show, don't tell'.' Maria Durbán, University Carlos III de MadridTable of Contents1. Introduction; 2. Bases, penalties, and likelihoods; 3. Optimal smoothing in action; 4. Multidimensional smoothing; 5. Smoothing of scale and shape; 6. Complex counts and composite links; 7. Signal regression; 8. Special subjects; A. P-splines for the impatient; B. P-splines and competitors; C. Computational details; D. Array algorithms; E. Mixed model equations; F. Standard errors in detail; G. The website.
£49.39
O'Reilly Media Scaling Graph Learning for the Enterprise
Book Synopsis
£47.99
Oxford University Press, USA Perspectives on Adaptation in Natural and Artificial Systems
Book SynopsisThis title consists of 17 papers on the contributions of John Holland by a group of scholars from a wide range of fields, including the Nobel laureates Kenneth Arrow and Herbert Simon, and also Douglas Hofstadter, Brian Arthur, Robert Axelrod, and Melanie Mitchell.Table of ContentsLashon Booker, Stephanie Forrest, Melanie Mitchell, and Rick Riolo: Introduction: Adaptation, Evolution, and Intelligence PART 1: GENETIC ALGOROTHMS AND BEYOND 1: Kenneth DeJong: Genetic Algorithms: A 30 Year Perspective 2: John R. Koza: Human-Competitive Machine Intelligence by Means of Genetic Algorithms 3: David E. Goldberg: John Holland, Facetwise models, and Economy of Thought PART 2: COMPUTATION, ARTIFICIAL INTELLIGENCE, AND BEYOND 4: Arthur W. Burks: An Early Graduate Program in Computers and Communications 5: Oliver G. Selfridge: Had We But World Enough and Time 6: Bernard P. Zeigler: Discrete Event Abstraction: An Emerging Paradigm for Modeling Complex Adaptive Systems 7: Herbert A. Simon: Good Old-Fashioned AI and Genetic Algorithms: An Exercise in Translation Scholarship 8: Douglad R. Hofstadter: Moore's Law, Artificial Evolutionm and the Fate of Humanity PART 3: THE NATURAL WORLD AND BEYOND 9: Julian Adams: Evolution of Complexity in Microbial Populations 10: Bobbi S. Low, Doug Finkbeiner, and Carl Simon: Favored Places in the Selfish Herd: Trading Off Food and Security 11: Rick Riolo, Robert Axelrod, and Michael D. Cohen: Tags, Interaction Patterns and the Evolution of Cooperation 12: Robert G. Reynolds and Salah Saleem: The Impact of Environmental Dynamics on Cultural Emergence 13: Kenneth J. Arrow: John Holland and the Evolution of Economics 14: W. Brian Arthur: Cognition: The Black Box of Economics Index
£90.00
Cambridge University Press Neural Network Learning Theoretical Foundations
Book SynopsisThis book describes theoretical advances in the study of artificial neural networks. It explores probabilistic models of supervised learning problems, and addresses the key statistical and computational questions. Research on pattern classification with binary-output networks is surveyed, including a discussion of the relevance of the VapnikâChervonenkis dimension, and calculating estimates of the dimension for several neural network models. A model of classification by real-output networks is developed, and the usefulness of classification with a 'large margin' is demonstrated. The authors explain the role of scale-sensitive versions of the VapnikâChervonenkis dimension in large margin classification, and in real prediction. They also discuss the computational complexity of neural network learning, describing a variety of hardness results, and outlining two efficient constructive learning algorithms. The book is self-contained and is intended to be accessible to researchers and graduaTrade Review'The book is a useful and readable mongraph. For beginners it is a nice introduction to the subject, for experts a valuable reference.' Zentralblatt MATHTable of Contents1. Introduction; Part I. Pattern Recognition with Binary-output Neural Networks: 2. The pattern recognition problem; 3. The growth function and VC-dimension; 4. General upper bounds on sample complexity; 5. General lower bounds; 6. The VC-dimension of linear threshold networks; 7. Bounding the VC-dimension using geometric techniques; 8. VC-dimension bounds for neural networks; Part II. Pattern Recognition with Real-output Neural Networks: 9. Classification with real values; 10. Covering numbers and uniform convergence; 11. The pseudo-dimension and fat-shattering dimension; 12. Bounding covering numbers with dimensions; 13. The sample complexity of classification learning; 14. The dimensions of neural networks; 15. Model selection; Part III. Learning Real-Valued Functions: 16. Learning classes of real functions; 17. Uniform convergence results for real function classes; 18. Bounding covering numbers; 19. The sample complexity of learning function classes; 20. Convex classes; 21. Other learning problems; Part IV. Algorithmics: 22. Efficient learning; 23. Learning as optimisation; 24. The Boolean perceptron; 25. Hardness results for feed-forward networks; 26. Constructive learning algorithms for two-layered networks.
£47.99
Cambridge University Press The Text Mining Handbook
Book SynopsisPresents a comprehensive discussion of the state-of-the-art in text mining and link detection. In addition to providing an in-depth examination of core text mining and link detection algorithms and operations, the book examines advanced pre-processing techniques, knowledge representation considerations, and visualization approaches, ending with real-world, mission-critical applications.Trade Review' … buy the book. This book is definitely worth having in your book shelf as a handy reference.' IAPR NewsletterTable of Contents1. Introduction to text mining; 2. Core text mining operations; 3. Text mining preprocessing techniques; 4. Categorization; 5. Clustering; 6. Information extraction; 7. Probabilistic models for Information extraction; 8. Preprocessing applications using probabilistic and hybrid approaches; 9. Presentation-layer considerations for browsing and query refinement; 10. Visualization approaches; 11. Link analysis; 12. Text mining applications; Appendix; Bibliography.
£74.99
Cambridge University Press Algebraic Geometry and Statistical Learning Theory 25 Cambridge Monographs on Applied and Computational Mathematics Series Number 25
Book SynopsisSure to be influential, this book lays the foundations for the use of algebraic geometry in statistical learning theory. Many widely used statistical models and learning machines applied to information science have a parameter space that is singular: mixture models, neural networks, HMMs, Bayesian networks, and stochastic context-free grammars are major examples. Algebraic geometry and singularity theory provide the necessary tools for studying such non-smooth models. Four main formulas are established: 1. the log likelihood function can be given a common standard form using resolution of singularities, even applied to more complex models; 2. the asymptotic behaviour of the marginal likelihood or 'the evidence' is derived based on zeta function theory; 3. new methods are derived to estimate the generalization errors in Bayes and Gibbs estimations from training errors; 4. the generalization errors of maximum likelihood and a posteriori methods are clarified by empirical process theory oTrade Review"Overall, the many insightful remarks and simple direct language make the book a pleasure to read." Shaowei Lin, Mathematical ReviewsTable of ContentsPreface; 1. Introduction; 2. Singularity theory; 3. Algebraic geometry; 4. Zeta functions and singular integral; 5. Empirical processes; 6. Singular learning theory; 7. Singular learning machines; 8. Singular information science; Bibliography; Index.
£76.99
Cambridge University Press Statistical Methods for Recommender Systems
Book SynopsisThis book is for researchers and students in statistics, data mining, computer science, machine learning, marketing and also practitioners who implement recommender systems. It provides an in-depth discussion of challenges encountered in deploying real-life large-scale systems and state-of-the-art solutions in personalization, explore/exploit, dimension reduction and multi-objective optimization.Trade Review'This book provides a comprehensive guide to state-of-the-art statistical techniques that are used to power recommender systems. … The text is authoritative and well written, with the authors drawing on their extensive experience of researching, implementing and evaluating real-world recommender systems. The book considers the underlying mathematics of the techniques it describes and, as such, is aimed at a readership with a strong background in statistics and cognate subjects. However, while readers without such a background are likely to find the mathematics somewhat challenging, the prose descriptions are highly readable and enable readers to understand the key principles and ideas which underpin the various approaches. This book should be of interest to those involved with recommender systems as well as to those with a broader interest in machine learning.' Patrick Hill, BCS: The Chartered Institute for IT (www.bcs.org)Table of ContentsPart I. Introduction: 1. Introduction; 2. Classical methods; 3. Explore/exploit for recommender problems; 4. Evaluation methods; Part II. Common Problem Settings: 5. Problem settings and system architecture; 6. Most-popular recommendation; 7. Personalization through feature-based regression; 8. Personalization through factor models; Part III. Advanced Topics: 9. Factorization through latent dirichlet allocation; 10. Context-dependent recommendation; 11. Multi-objective optimization.
£47.99
Cambridge University Press Legal Informatics
Book SynopsisThis groundbreaking work offers a first-of-its-kind overview of legal informatics, the academic discipline underlying the technological transformation and economics of the legal industry. Edited by Daniel Martin Katz, Ron Dolin, and Michael J. Bommarito, and featuring contributions from more than two dozen academic and industry experts, chapters cover the history and principles of legal informatics and background technical concepts including natural language processing and distributed ledger technology. The volume also presents real-world case studies that offer important insights into document review, due diligence, compliance, case prediction, billing, negotiation and settlement, contracting, patent management, legal research, and online dispute resolution. Written for both technical and non-technical readers, Legal Informatics is the ideal resource for anyone interested in identifying, understanding, and executing opportunities in this exciting field.Trade Review'This is not just a book. It is a movement. In this superb collection, Katz, Dolin, and Bommarito not only provide a comprehensive primer on why the market for legal services is being disrupted, and how this disruption will take place, but also lay the groundwork for a whole new discipline - legal informatics - that can supply the intellectual and practical scaffolding for the new legal world these changes will bring into being. It is required reading for anyone seeking to participate in this transformation, or who will be affected by it - which, as this seminal volume makes clear, is all of us.' David Wilkins, Lester Kissel Professor of Law and Faculty Director of the Center on the Legal Profession, Harvard Law School'This volume is a treasure trove for anyone interested in how technology can enable and enhance the delivery of legal services. The editors have done a first rate job of curating the research, insights and practical experiences of many of the world's leading experts. The field of legal informatics, at least 60 years of age, at last has its own definitive text.' Richard Susskind OBE, President of the Society for Computers and Law, author of Tomorrow's Lawyers'Informatics is not the frontier of law. It has lurched toward the center, shoved forward by the rush to embed algorithmic decision making into everything from cars to phones to facial recognition technology. Whether you are a newcomer in search of a curated overview, or a #legaltech frequent flyer looking for the state of the art, this is the one book you need to make sense of it all.' Eddie Hartman, Co-founder of LegalZoom, Partner at Simon-Kucher & PartnersTable of ContentsPart I. Introduction to Legal Informatics: 1. Motivation and Rationale for this Book Daniel Martin Katz, Ron Dolin and Michael J. Bommarito II; 2. Technology Issues in Legal Philosophy Ron Dolin; 3. The Origins and History of Legal Informatics Michael J. Bommarito II; Part II. Legal Informatics – Building Blocks and Core Concepts: 4. Representation of Legal Information Katie Atkinson; 5. Information Intermediation Ron Dolin; 6. Preprocessing Data Michael J. Bommarito II; 7. XML in Law: The Role of Standards in Legal Informatics Ron Dolin; 8. Document Assembly and Automation Marc Lauritsen; 9. AI + Law: An Overview Daniel Martin Katz; 10. Machine Learning Daniel Martin Katz and John Nay; 11. Natural Language Processing for Legal Texts John Nay; 12. Introduction to Blockchain and Cryptography Nelson M. Rosario; 13. Legal Informatics-Based Technology in Broader Workflows Kenneth Grady; 14. Gamification of Work and Feedback Systems Stephanie Kimbro; 15. Introduction to Design Thinking for Law Margaret Hagan; 16. Measuring Legal Quality Ron Dolin; Part III. Legal Informatics Use Cases: 17. Contract Analytics Noah Waisberg: 18. Contracts as Interfaces: Visual Representation Patterns in Contract Design Helena Haapio and Stefania Passera; 19. Distributed Ledgers, Cryptography, and Smart Contracts Nina Gunther Kilbride; 20. Patent Analytics: Information from Innovation Jevin D. West and Andrew W. Torrance; 21. The Core Concepts of E-Discovery Jonathan Kerry-Tyerman and AJ Shankar; 22. Predictive Coding in E-Discovery and The NexLP Story Engine Irina Matveeva; 23. Examining Public Court Data to Understand and Predict Bankruptcy Case Results Warren Agin; 24. Fastcase, and the Visual Understanding of Judicial Precedents Ed Walters and Jeff Asjes; 25. Mining Information from Statutory Texts in a Public Health Domain Kevin Ashley; 26. Gov2Vec: A Case Study in Text Model Application to Government Data John Nay; 27. Representation and Automation of Legal Information Katie Atkinson; 28. Online Dispute Resolution Dave Orr and Colin Rule; 29. Access to Justice and Technology: Reaching a Greater Future for Legal Aid Ronald W. Staudt and Alexander F. A. Rabanal; 30. Designing Legal Experiences: Online Communication and Resolution in Courts Maximilian A. Bulinski and J.J. Prescott; Part IV. Legal Informatics in the Industrial Context: 31. Adaptive Innovation: The Innovator's Dilemma in Big Law Ron Dolin and Thomas Buley; 32. Legal Data Access Christine Bannan; 33. A History of Knowledge Management at Littler Mendelsohn Scott Rechtshaffen; 34. Google Legal Operations Mary O'Carroll amd Stephanie Kimbro.
£147.25
Elsevier Science & Technology Artificial Intelligence: A New Synthesis
Book SynopsisIntelligent agents are employed as the central characters in this introductory text. Beginning with elementary reactive agents, Nilsson gradually increases their cognitive horsepower to illustrate the most important and lasting ideas in AI. Neural networks, genetic programming, computer vision, heuristic search, knowledge representation and reasoning, Bayes networks, planning, and language understanding are each revealed through the growing capabilities of these agents. A distinguishing feature of this text is in its evolutionary approach to the study of AI. This book provides a refreshing and motivating synthesis of the field by one of AI's master expositors and leading researches.Table of ContentsReactive Machines. Neural Networks. Machine Evolution. State Machines. Robot Vision. Search in State Spaces. Agents that Plan. Uninformed Search. Heuristic Search. Planning, Acting and Learning. Alternative Search. Knowledge Representation and Reasoning. The Propositional Calculus. The Predicate Calculus. Knowledge-based Systems. Representing Common sense Knowledge. Reasoning with Uncertain Information. Learning and Acting with Bayes Nets. Planning Methods Based on Logic. The Situation Calculus. Planning. Communication and Integration. Multiple Agents. Communication Among Agents. Agent Architectures.
£54.89
APress Handson Guide to Apache Spark 3
Book SynopsisThis book explains how to scale Apache Spark 3 to handle massive amounts of data, either via batch or streaming processing. It covers how to use Spark's structured APIs to perform complex data transformations and analyses you can use to implement end-to-end analytics workflows.This book covers Spark 3's new features, theoretical foundations, and application architecture. The first section introduces the Apache Spark ecosystem as a unified engine for large scale data analytics, and shows you how to run and fine-tune your first application in Spark. The second section centers on batch processing suited to end-of-cycle processing, and data ingestion through files and databases. It explains Spark DataFrame API as well as structured and unstructured data with Apache Spark. The last section deals with scalable, high-throughput, fault-tolerant streaming processing workloads to process real-time data. Here you'll learn about Apache Spark Streaming's execution model, the architecture of Spark STable of ContentsPart I. Apache Spark Batch Data ProcessingChapter 1: Introduction to Apache Spark for Large-Scale Data Analytics1.1. What is Apache Spark? 1.2. Spark Unified Analytics1.3. Batch vs Streaming Data1.4. Spark EcosystemChapter 2: Getting Started with Apache Spark2.2. Scala and PySpark Interfaces2.3. Spark Application Concepts2.4. Transformations and Actions in Apache Spark2.5. Lazy Evaluation in Apache Spark2.6. First Application in Spark2.7. Apache Spark Web UIChapter 3: Spark Dataframe APIChapter 4: Spark Dataset APIChapter 5: Structured and Unstructured Data with Apache Spark5.1. Data Sources5.2. Generic Load/Save Functions5.3. Generic File Source Options5.4. Parquet Files5.5. ORC Files5.6. JSON Files5.7. CSV Files5.8. Text Files5.9. Hive Tables5.10. JDBC To Other DatabasesChapter 6: Spark Machine Learning with MLlibPart II. Spark Data StreamingChapter 7: Introduction to Apache Spark Streaming7.1. Apache Spark Streaming’s Execution Model7.2. Stream Processing Architectures7.3. Architecture of Spark Streaming: Discretized Streams7.4. Benefits of Discretized Stream Processing7.4.1. Dynamic Load Balancing7.4.2. Fast Failure and Straggler RecoveryChapter 8: Structured Streaming8.1. Streaming Analytics8.2. Connecting to a Stream8.3. Preparing the Data in a Stream8.4. Operations on a Streaming DatasetChapter 9: Structured Streaming Sources9.1. File Sources9.2. Apache Kafka Source9.3. A Rate SourceChapter 10: Structured Streaming Sinks10.1. Output Modes10.2. Output Sinks10.3. File Sink10.4. The Kafka Sink10.5. The Memory Sink 10.6. Streaming Table APIs10.7. Triggers10.8. Managing Streaming Queries10.9. Monitoring Streaming Queries10.9.1. Reading Metrics Interactively10.9.2. Reporting Metrics programmatically using Asynchronous APIs10.9.3. Reporting Metrics using Dropwizard10.9.4. Recovering from Failures with Checkpointing10.9.5. Recovery Semantics after Changes in a Streaming QueryChapter 11: Future Directions for Spark Streaming11.1. Backpressure11.2. Dynamic Scaling11.3. Event time and out-of-order data11.4. UI enhancements11.5. Continuous ProcessingChapter 12: Watermarks. A deep survey of temporal progress metrics
£46.74
BCS Learning & Development Limited Artificial Intelligence and Software Testing:
Book SynopsisWINNER: Independent Press Awards 2023 - Category: Technology AI presents a new paradigm in software development, representing the biggest change to how we think about quality and testing in decades. Many of the well known issues around AI, such as bias, manifest themselves as quality management problems. This book, aimed at testing and quality management practitioners who want to understand more, covers trustworthiness of AI and the complexities of testing machine learning systems, before pivoting to how AI can be used itself in software test automation.Trade ReviewA brilliant reference with a focus on introducing the reader to new AI ideas and challenges. The danger with AI and software testing is the mistaken belief that people understand it all. This book addresses this issue by opening the reader up to a rich source of references & useful concepts using use cases, models and references, to both stimulate and challenge the reader's own knowledge of this broad subject. Highly recommended. -- Paul Mowat MBCS CITP, BCS SiGIST Social Media Secretary & Committee Member, Quality Test Engineer Director, Deloitte UKAI-based systems conquer more and more areas of our daily life. People are concerned whether these systems are trustworthy. 'Artificial Intelligence and Software Testing' tackles this issue and provides an insight into AI quality and how it differs from conventional software quality, and where the difficulties and challenges are in testing machine learning systems. A great introduction into this topic and must read for all interested in building AI-based systems that you can trust. -- Klaudia Dussa-Zieger, Chair GTB & Vice President ISTQB®, Head of ISTQB® Certified Tester AI Testing (CT-AI) taskforceIn the ever expansive and evolving virtual domain, the prominence of AI is becoming more and more prolific, and this evolution will not be without its challenges. This title provides an excellent resource into the potential dilemmas faced in this evolutionary field as the virtual, cognitive, and physical spaces become more interlinked with the dawn of the metaverse. The part that humans play in the growth, development and testing of AI is discussed. Supported by a wealth of experience, research, and evidence from the authors, the title provides a great introduction to and understanding of AI and software testing. Highly recommended for all with an interest in this area. -- Jonathan Miles MBA BSc(Hons) FCMI, Head of Strategic Intelligence, MimecastShift Right! A concept you won’t find in ‘The Seven Principles of Testing’. 'Artificial Intelligence and Software Testing' puts the principles into perspective. Not only does it explore early testing, but it also looks at the concept of exhaustive testing thoroughly and effectively. As a trainer of software testing I will definitely use all this book has to offer. Guiding the next generation of testers to question the intricacies of machine learning. A must for anyone in tech, not just software testers. -- Rachel Hurley MBCS TAP.dip, Technical Trainer (Software Testing)As the title describes, this book is a robust AI and ML testing exploration that also dives into the juxtaposition of the trustworthiness and bias in AI systems. It touches on the basis of ontologies and how to enable the considerable impact of testing and monitoring of AI-based systems. After reading this you would be able to answer an important challenge: how to determine that your AI system has been extensively tested? -- Dina Dede, AI/ML and Cloud Architect Lead, UKThis book beautifully captures the game-changing complexity of artificial intelligence (AI) and the traditional discipline of software quality management. It is a comprehensive manual addressing the conundrum and tantalizing promise of both disciplines with good pace and a distinct future-present context. Forget waterfall and DevOps, we’re right shifting into OpsDev, AIOps and digital twins in the metaverse, so things are about to get a whole lot more interesting. Excellent effort, and a much-needed treatment of this topic by true experts. -- Jude Umeh FBCS CITP, Senior Program Architect, Salesforce'Artificial Intelligence and Software Testing' is a great read. The vast experience of the authors is evident as they comprehensively explain the challenges and benefits of not only applying AI to testing, but also testing the AI software itself. I found the insight into the shift-right approach and its application during the development of the test and trace application fascinating. A must read for any testing/QA professional plus any C-suite looking to rapidly increase their ROI on testing. -- Anil Pande, Managing Partner, TestPro Consulting LtdThis book is a very good introduction to using AI in software testing as well as testing AI systems, covering several relevant topics like societal risk, bias, ethical behavior, quality, trustworthiness, and the problems associated with AI/ML systems. I specifically liked the section that details on the problems associated with AI/ML systems. I would recommend this book to anyone who is starting their study on software testing vis-a-vis AI/ML systems. -- Venkat Ramakrishnan, Software Quality Leader And Software Testing Technologist'Artificial Intelligence and Software Testing' is a valuable resource for anyone curious in how to approach testing AI models as they expand into our daily lives. This is a clear, informative read which discusses within each chapter different testing challenges with AI software and advice on how to handle them effectively. I can highly recommend this to testers and students alike. -- Katy Hannath BSc(Hons), MSc in Artificial Intelligence and Data Science student, & Quality Assurance Tester, VISR DynamicsThis book is an exceptionally practical resource which is a remarkable reference guide to understanding the foundations of AI & ML for anyone wishing to build a career in AI or define a test approach. It has a clear, direct, and concise explanation of AI, ML, ethics, ontology, quality, bias, challenges, test automation, and the significance of ‘shift-right’ testing. It offers thorough, data-driven and real-world examples that bring together the rich wealth of experience from these expert authors and authorities in this area. -- Boby Jose BSc MBA MBCS, Author of BCS publication ‘Test Automation: A manager’s guide’What an exciting and relevant publication! Beyond the positive game-changing societal benefits delivered by AI, it has proven equally disruptive to all aspects of software engineering including software testing. This book provides great insight into new build and test design techniques to augment our traditional thinking. An essential guide for technology leaders and test professionals alike, looking to understand how to approach the critical problem of building and testing today’s complex and often unpredictable AI systems. -- Jack Mortassagne, Director at Cigniti Technologies and TMMI Accredited AssessorThis is a great book for those who want to gain more insight into how AI will affect the software testing profession. The writers introduce the challenges in AI in an easy-to-understand manner, while the case studies showcased are extremely interesting and contemporary, clearly exemplifying the topics presented. Brilliant read and highly recommended! -- Dr Diana Hintea BEng(Hons) PhD SFHEA, Associate Head of School (School of Computing, Electronics and Mathematics), Coventry UniversityIn a time the promised paradigm shift of Artificial intelligence is starting to have a real-world impact, this is a vitally important book. It explains the social, ethical, and technical concerns around AI in an easy to understand way, making a complex subject easily accessible. Everyone involved in IT is likely to be impacted by AI whether from a business, technical, ethical, or quality point of view and so this book will be an invaluable resource for everyone in IT. As a Testing and Quality specialist, this is going to have pride of place on my bookshelf as a practical, real-world reference for helping me navigate testing and quality in the emerging world of AI. -- Bryan Jones MBCS, Director of Testing Practice, Sopra Steria Private SectorThis book is a must-read for anyone in software testing with responsibility for quality assuring AI technology that must engender public trust. With topics that feel both familiar and challenging, the authors confidently explore a range of subjects to broaden and deepen the reader’s understanding of the intersection of AI and testing. -- Bronia Anderson-Kelly, IT change consultant, Sabiduria LtdThis book addresses an often ignored but critically important aspect of AI implementation: how to ensure that AI's are producing, and continue to produce, acceptable output. As AI is non-deterministic and complex, and dataset quality can be highly variable, it is notoriously difficult to determine suitable test cases for modern systems. In this book, the authors provide practical methods and examples that can be used to ensure AI quality, and as such is an extremely useful resource for anyone implementing systems involving AI and machine learning. -- Peter Brightwell MSc, Intelligent Automation Architect, NDL SoftwareTable of Contents Introduction AI Trustworthiness and Quality Quality and Bias Testing Machine Learning Systems AI-based Test Automation Ontologies for Software Testing Shifting Right into the Metaverse with Digital Twin Testing
£33.24
Packt Publishing Limited Machine Learning for OpenCV
Book SynopsisExpand your OpenCV knowledge and master key concepts of machine learning using this practical, hands-on guide. About This Book Load, store, edit, and visualize data using OpenCV and Python Grasp the fundamental concepts of classification, regression, and clustering Understand, perform, and experiment with machine learning techniques using this easy-to-follow guide Evaluate, compare, and choose the right algorithm for any taskWho This Book Is ForThis book targets Python programmers who are already familiar with OpenCV; this book will give you the tools and understanding required to build your own machine learning systems, tailored to practical real-world tasks. What You Will Learn Explore and make effective use of OpenCV's machine learning module Learn deep learning for computer vision with Python Master linear regression and regularization techniques Classify objects such as flower species, handwritten digits, and pedestrians Explore the effective use of support vector machines, boosted decision trees, and random forests Get acquainted with neural networks and Deep Learning to address real-world problems Discover hidden structures in your data using k-means clustering Get to grips with data pre-processing and feature engineeringIn DetailMachine learning is no longer just a buzzword, it is all around us: from protecting your email, to automatically tagging friends in pictures, to predicting what movies you like. Computer vision is one of today's most exciting application fields of machine learning, with Deep Learning driving innovative systems such as self-driving cars and Google's DeepMind. OpenCV lies at the intersection of these topics, providing a comprehensive open-source library for classic as well as state-of-the-art computer vision and machine learning algorithms. In combination with Python Anaconda, you will have access to all the open-source computing libraries you could possibly ask for. Machine learning for OpenCV begins by introducing you to the essential concepts of statistical learning, such as classification and regression. Once all the basics are covered, you will start exploring various algorithms such as decision trees, support vector machines, and Bayesian networks, and learn how to combine them with other OpenCV functionality. As the book progresses, so will your machine learning skills, until you are ready to take on today's hottest topic in the field: Deep Learning. By the end of this book, you will be ready to take on your own machine learning problems, either by building on the existing source code or developing your own algorithm from scratch!Style and approachOpenCV machine learning connects the fundamental theoretical principles behind machine learning to their practical applications in a way that focuses on asking and answering the right questions. This book walks you through the key elements of OpenCV and its powerful machine learning classes, while demonstrating how to get to grips with a range of models.
£44.00
Packt Publishing Limited Machine Learning with R Expert techniques for predictive modeling to solve all your data analysis problems 2nd Edition
£50.34
Packt Publishing Limited Advanced Deep Learning with R: Become an expert
Book SynopsisDiscover best practices for choosing, building, training, and improving deep learning models using Keras-R, and TensorFlow-R librariesKey Features Implement deep learning algorithms to build AI models with the help of tips and tricks Understand how deep learning models operate using expert techniques Apply reinforcement learning, computer vision, GANs, and NLP using a range of datasets Book DescriptionDeep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data. Advanced Deep Learning with R will help you understand popular deep learning architectures and their variants in R, along with providing real-life examples for them.This deep learning book starts by covering the essential deep learning techniques and concepts for prediction and classification. You will learn about neural networks, deep learning architectures, and the fundamentals for implementing deep learning with R. The book will also take you through using important deep learning libraries such as Keras-R and TensorFlow-R to implement deep learning algorithms within applications. You will get up to speed with artificial neural networks, recurrent neural networks, convolutional neural networks, long short-term memory networks, and more using advanced examples. Later, you'll discover how to apply generative adversarial networks (GANs) to generate new images; autoencoder neural networks for image dimension reduction, image de-noising and image correction and transfer learning to prepare, define, train, and model a deep neural network. By the end of this book, you will be ready to implement your knowledge and newly acquired skills for applying deep learning algorithms in R through real-world examples.What you will learn Learn how to create binary and multi-class deep neural network models Implement GANs for generating new images Create autoencoder neural networks for image dimension reduction, image de-noising and image correction Implement deep neural networks for performing efficient text classification Learn to define a recurrent convolutional network model for classification in Keras Explore best practices and tips for performance optimization of various deep learning models Who this book is forThis book is for data scientists, machine learning practitioners, deep learning researchers and AI enthusiasts who want to develop their skills and knowledge to implement deep learning techniques and algorithms using the power of R. A solid understanding of machine learning and working knowledge of the R programming language are required.Table of ContentsTable of Contents Revisiting Deep Learning architecture and techniques Deep Neural Networks for multiclass classification Deep Neural Networks for regression Image classification and recognition Image classification using convolutional neural networks Applying Autoencoder neural networks using Keras Image classification for small data using transfer learning Creating new images using generative adversarial networks Deep network for text classification Text classification using recurrent neural networks Text classification using Long Short-Term Memory Network Text classification using convolutional recurrent networks Tips, tricks and the road ahead
£34.19
Packt Publishing Limited The The TensorFlow Workshop: A hands-on guide to
Book SynopsisGet started with TensorFlow fundamentals to build and train deep learning models with real-world data, practical exercises, and challenging activitiesKey Features Understand the fundamentals of tensors, neural networks, and deep learning Discover how to implement and fine-tune deep learning models for real-world datasets Build your experience and confidence with hands-on exercises and activities Book DescriptionGetting to grips with tensors, deep learning, and neural networks can be intimidating and confusing for anyone, no matter their experience level. The breadth of information out there, often written at a very high level and aimed at advanced practitioners, can make getting started even more challenging.If this sounds familiar to you, The TensorFlow Workshop is here to help. Combining clear explanations, realistic examples, and plenty of hands-on practice, it’ll quickly get you up and running. You’ll start off with the basics – learning how to load data into TensorFlow, perform tensor operations, and utilize common optimizers and activation functions. As you progress, you’ll experiment with different TensorFlow development tools, including TensorBoard, TensorFlow Hub, and Google Colab, before moving on to solve regression and classification problems with sequential models. Building on this solid foundation, you’ll learn how to tune models and work with different types of neural network, getting hands-on with real-world deep learning applications such as text encoding, temperature forecasting, image augmentation, and audio processing.By the end of this deep learning book, you’ll have the skills, knowledge, and confidence to tackle your own ambitious deep learning projects with TensorFlow.What you will learn Get to grips with TensorFlow’s mathematical operations Pre-process a wide variety of tabular, sequential, and image data Understand the purpose and usage of different deep learning layers Perform hyperparameter-tuning to prevent overfitting of training data Use pre-trained models to speed up the development of learning models Generate new data based on existing patterns using generative models Who this book is forThis TensorFlow book is for anyone who wants to develop their understanding of deep learning and get started building neural networks with TensorFlow. Basic knowledge of Python programming and its libraries, as well as a general understanding of the fundamentals of data science and machine learning, will help you grasp the topics covered in this book more easily.Table of ContentsTable of Contents Introduction to Machine Learning with TensorFlow Loading and Processing Data TensorFlow Development Regression and Classification Models Classification Models Regularization and Hyperparameter Tuning Convolutional Neural Networks Pre-Trained Networks Recurrent Neural Networks Custom TensorFlow Components Generative Models
£30.99
Cornerstone Artificial Intelligence (WIRED guides): How
Book SynopsisThe past decade has witnessed extraordinary advances in artificial intelligence. But what precisely is it and where does its future lie?In this brilliant, one-stop guide WIRED journalist Matt Burgess explains everything you need to know about AI. He describes how it works. He looks at the ways in which it has already brought us everything from voice recognition software to self-driving cars, and explores its potential for further revolutionary change in almost every area of our daily lives. He examines the darker side of machine learning: its susceptibility to hacking; its tendency to discriminate against particular groups; and its potential misuse by governments. And he addresses the fundamental question: can machines become as intelligent as human beings?Trade ReviewIn this book Burgess manages to cover all the key AI trends and developments over the last 60 years . . . delivers an informative and readable guide to all the main events that have taken place to date . . . We found this one helpful for a new or general reader and would recommend it to those looking for a good place to start in this field. * Irish Tech News *
£9.49
Springer Nature Switzerland AG Intelligent Random Walk: An Approach Based on
Book SynopsisThis book examines the intelligent random walk algorithms based on learning automata: these versions of random walk algorithms gradually obtain required information from the nature of the application to improve their efficiency. The book also describes the corresponding applications of this type of random walk algorithm, particularly as an efficient prediction model for large-scale networks such as peer-to-peer and social networks. The book opens new horizons for designing prediction models and problem-solving methods based on intelligent random walk algorithms, which are used for modeling and simulation in various types of networks, including computer, social and biological networks, and which may be employed a wide range of real-world applications.Table of ContentsRandom walk algorithms: Definitions, weaknesses, and learning automata based approach.- Intelligent Models of Random Walk.- Applications.- Conclusions.
£42.74
Springer Nature Switzerland AG Applied Machine Learning
Book SynopsisMachine learning methods are now an important tool for scientists, researchers, engineers and students in a wide range of areas. This book is written for people who want to adopt and use the main tools of machine learning, but aren’t necessarily going to want to be machine learning researchers. Intended for students in final year undergraduate or first year graduate computer science programs in machine learning, this textbook is a machine learning toolkit. Applied Machine Learning covers many topics for people who want to use machine learning processes to get things done, with a strong emphasis on using existing tools and packages, rather than writing one’s own code.A companion to the author's Probability and Statistics for Computer Science, this book picks up where the earlier book left off (but also supplies a summary of probability that the reader can use).Emphasizing the usefulness of standard machinery from applied statistics, this textbook gives an overview of the major applied areas in learning, including coverage of:• classification using standard machinery (naive bayes; nearest neighbor; SVM)• clustering and vector quantization (largely as in PSCS)• PCA (largely as in PSCS)• variants of PCA (NIPALS; latent semantic analysis; canonical correlation analysis)• linear regression (largely as in PSCS)• generalized linear models including logistic regression• model selection with Lasso, elasticnet• robustness and m-estimators• Markov chains and HMM’s (largely as in PSCS)• EM in fairly gory detail; long experience teaching this suggests one detailed example is required, which students hate; but once they’ve been through that, the next one is easy• simple graphical models (in the variational inference section)• classification with neural networks, with a particular emphasis onimage classification• autoencoding with neural networks• structure learningTable of Contents1. Learning to Classify.- 2. SVM’s and Random Forests.- 3. A Little Learning Theory.- 4. High-dimensional Data.- 5. Principal Component Analysis.- 6. Low Rank Approximations.- 7. Canonical Correlation Analysis.- 8. Clustering.- 9. Clustering using Probability Models.- 10. Regression.- 11. Regression: Choosing and Managing Models.- 12. Boosting.- 13. Hidden Markov Models.- 14. Learning Sequence Models Discriminatively.- 15. Mean Field Inference.- 16. Simple Neural Networks.- 17. Simple Image Classifiers.- 18. Classifying Images and Detecting Objects.- 19. Small Codes for Big Signals.- Index.
£62.99
Springer Nature Switzerland AG Deep Learning Architectures: A Mathematical
Book SynopsisThis book describes how neural networks operate from the mathematical point of view. As a result, neural networks can be interpreted both as function universal approximators and information processors. The book bridges the gap between ideas and concepts of neural networks, which are used nowadays at an intuitive level, and the precise modern mathematical language, presenting the best practices of the former and enjoying the robustness and elegance of the latter.This book can be used in a graduate course in deep learning, with the first few parts being accessible to senior undergraduates. In addition, the book will be of wide interest to machine learning researchers who are interested in a theoretical understanding of the subject. Trade Review“This book is useful to students who have already had an introductory course in machine learning and are further interested to deepen their understanding of the machine learning material from the mathematical point of view.” (T. C. Mohan, zbMATH 1441.68001, 2020)Table of ContentsIntroductory Problems.- Activation Functions.- Cost Functions.- Finding Minima Algorithms.- Abstract Neurons.- Neural Networks.- Approximation Theorems.- Learning with One-dimensional Inputs.- Universal Approximators.- Exact Learning.- Information Representation.- Information Capacity Assessment.- Output Manifolds.- Neuromanifolds.- Pooling.- Convolutional Networks.- Recurrent Neural Networks.- Classification.- Generative Models.- Stochastic Networks.- Hints and Solutions.
£71.99
Springer Nature Switzerland AG Linear Algebra and Optimization for Machine
Book SynopsisThis textbook introduces linear algebra and optimization in the context of machine learning. Examples and exercises are provided throughout the book. A solution manual for the exercises at the end of each chapter is available to teaching instructors. This textbook targets graduate level students and professors in computer science, mathematics and data science. Advanced undergraduate students can also use this textbook. The chapters for this textbook are organized as follows:1. Linear algebra and its applications: The chapters focus on the basics of linear algebra together with their common applications to singular value decomposition, matrix factorization, similarity matrices (kernel methods), and graph analysis. Numerous machine learning applications have been used as examples, such as spectral clustering, kernel-based classification, and outlier detection. The tight integration of linear algebra methods with examples from machine learning differentiates this book from generic volumes on linear algebra. The focus is clearly on the most relevant aspects of linear algebra for machine learning and to teach readers how to apply these concepts.2. Optimization and its applications: Much of machine learning is posed as an optimization problem in which we try to maximize the accuracy of regression and classification models. The “parent problem” of optimization-centric machine learning is least-squares regression. Interestingly, this problem arises in both linear algebra and optimization, and is one of the key connecting problems of the two fields. Least-squares regression is also the starting point for support vector machines, logistic regression, and recommender systems. Furthermore, the methods for dimensionality reduction and matrix factorization also require the development of optimization methods. A general view of optimization in computational graphs is discussed together with its applications to back propagation in neural networks. A frequent challenge faced by beginners in machine learning is the extensive background required in linear algebra and optimization. One problem is that the existing linear algebra and optimization courses are not specific to machine learning; therefore, one would typically have to complete more course material than is necessary to pick up machine learning. Furthermore, certain types of ideas and tricks from optimization and linear algebra recur more frequently in machine learning than other application-centric settings. Therefore, there is significant value in developing a view of linear algebra and optimization that is better suited to the specific perspective of machine learning. Trade Review“Based on the topics covered and the excellent presentation, I would recommend Aggarwal's book over these other books for an advanced undergraduate or beginning graduate course on mathematics for data science.” (Brian Borchers, MAA Reviews, March 28, 2021)“This book should be of interest to graduate students in engineering, applied mathematics, and other fields requiring an understanding of the mathematical underpinnings of machine learning.” (IEEE Control Systems Magazine, Vol. 40 (6), December, 2020)Table of ContentsPreface.- 1 Linear Algebra and Optimization: An Introduction.- 2 Linear Transformations and Linear Systems.- 3 Eigenvectors and Diagonalizable Matrices.- 4 Optimization Basics: A Machine Learning View.- 5 Advanced Optimization Solutions.- 6 Constrained Optimization and Duality.- 7 Singular Value Decomposition.- 8 Matrix Factorization.- 9 The Linear Algebra of Similarity.- 10 The Linear Algebra of Graphs.- 11 Optimization in Computational Graphs.- Index.
£42.74
Springer Nature Switzerland AG Machine Learning in Finance: From Theory to
Book SynopsisThis book introduces machine learning methods in finance. It presents a unified treatment of machine learning and various statistical and computational disciplines in quantitative finance, such as financial econometrics and discrete time stochastic control, with an emphasis on how theory and hypothesis tests inform the choice of algorithm for financial data modeling and decision making. With the trend towards increasing computational resources and larger datasets, machine learning has grown into an important skillset for the finance industry. This book is written for advanced graduate students and academics in financial econometrics, mathematical finance and applied statistics, in addition to quants and data scientists in the field of quantitative finance. Machine Learning in Finance: From Theory to Practice is divided into three parts, each part covering theory and applications. The first presents supervised learning for cross-sectional data from both a Bayesian and frequentist perspective. The more advanced material places a firm emphasis on neural networks, including deep learning, as well as Gaussian processes, with examples in investment management and derivative modeling. The second part presents supervised learning for time series data, arguably the most common data type used in finance with examples in trading, stochastic volatility and fixed income modeling. Finally, the third part presents reinforcement learning and its applications in trading, investment and wealth management. Python code examples are provided to support the readers' understanding of the methodologies and applications. The book also includes more than 80 mathematical and programming exercises, with worked solutions available to instructors. As a bridge to research in this emergent field, the final chapter presents the frontiers of machine learning in finance from a researcher's perspective, highlighting how many well-known concepts in statistical physics are likely to emerge as important methodologies for machine learning in finance.Trade Review“This book is, however, a well-structured and self-contained graduate textbook on ML applications in finance. Exercises and some applications are included at the end of each chapter and the Python code used in this book makes use of the Python Tensor Flow library. This book could also serve as a useful reference book for researchers and practitioners in quantitative finance.” (Gilles Teyssière, Mathematical Reviews, February, 2023)“Each part is introduced with background information, examples of relevant practical applications, and references to the most recent scientific literature. … The book covers all essential areas of machine learning with relevance to quantitative finance. … An additional strong advantage of this book is the clear and consistent structure of its chapters. … Overall, the book covers multiple machine learning approaches with advanced technical exposition and is therefore especially suitable as an academic reference point, especially on Reinforcement Learning.” (Antoniya Shivarova, Financial Markets and Portfolio Management, Issue 35, 2021)“This volume aims to present a broad yet technical treatment of (ML) algorithms used by financial practitioners and scholars alike. … the book fills a large void. … This encourages reproducibility as well as learning by doing, which is highly appreciated.” (Guillaume Coqueret, Quantitative Finance, October 15, 2020)Table of ContentsChapter 1. Introduction.- Chapter 2. Probabilistic Modeling.- Chapter 3. Bayesian Regression & Gaussian Processes.- Chapter 4. Feed Forward Neural Networks.- Chapter 5. Interpretability.- Chapter 6. Sequence Modeling.- Chapter 7. Probabilistic Sequence Modeling.- Chapter 8. Advanced Neural Networks.- Chapter 9. Introduction to Reinforcement learning.- Chapter 10. Applications of Reinforcement Learning.- Chapter 11. Inverse Reinforcement Learning and Imitation Learning.- Chapter 12. Frontiers of Machine Learning and Finance.
£62.99
Springer Nature Switzerland AG Open Source Intelligence and Cyber Crime: Social
Book SynopsisThis book shows how open source intelligence can be a powerful tool for combating crime by linking local and global patterns to help understand how criminal activities are connected. Readers will encounter the latest advances in cutting-edge data mining, machine learning and predictive analytics combined with natural language processing and social network analysis to detect, disrupt, and neutralize cyber and physical threats. Chapters contain state-of-the-art social media analytics and open source intelligence research trends. This multidisciplinary volume will appeal to students, researchers, and professionals working in the fields of open source intelligence, cyber crime and social network analytics. Chapter Automated Text Analysis for Intelligence Purposes: A Psychological Operations Case Study is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.Table of ContentsChapter1. Studying the Weaponization of Social Media: Case Studies of Anti-NATO Disinformation Campaigns.- Chapter2. Cognitively-Inspired Inference for Malware Task Indentation.- Chapter3. Beyond the ‘Silk Road’: Assessing Illicit Drug Marketplaces on the Public Web.- Chapter4. Protecting the Web from Misinformation.- Chapter5. Social Media for Mental Health: Data, Methods, and Findings.- Chapter6. Twitter Bots and the Swedish Election.- Chapter7. Automated Text Analysis for Intelligence Purposes: A Psychological Operations Case Study.- Chapter8. You are Known by Your Friends: Leveraging Network Metrics for Bot Detection in Twitter.- Chapter9. Inferring Systemic Nets with Applications to Islamist Forums.
£89.99
Springer Nature Switzerland AG Unsupervised Learning in Space and Time: A Modern
Book SynopsisThis book addresses one of the most important unsolved problems in artificial intelligence: the task of learning, in an unsupervised manner, from massive quantities of spatiotemporal visual data that are available at low cost. The book covers important scientific discoveries and findings, with a focus on the latest advances in the field. Presenting a coherent structure, the book logically connects novel mathematical formulations and efficient computational solutions for a range of unsupervised learning tasks, including visual feature matching, learning and classification, object discovery, and semantic segmentation in video. The final part of the book proposes a general strategy for visual learning over several generations of student-teacher neural networks, along with a unique view on the future of unsupervised learning in real-world contexts. Offering a fresh approach to this difficult problem, several efficient, state-of-the-art unsupervised learning algorithms are reviewed in detail, complete with an analysis of their performance on various tasks, datasets, and experimental setups. By highlighting the interconnections between these methods, many seemingly diverse problems are elegantly brought together in a unified way. Serving as an invaluable guide to the computational tools and algorithms required to tackle the exciting challenges in the field, this book is a must-read for graduate students seeking a greater understanding of unsupervised learning, as well as researchers in computer vision, machine learning, robotics, and related disciplines. Table of Contents1. Unsupervised Visual Learning: from Pixels to Seeing.- 2. Unsupervised Learning of Graph and Hypergraph Matching.- 3. Unsupervised Learning of Graph and Hypergraph Clustering.- 4. Feature Selection meets Unsupervised Learning.- 5. Unsupervised Learning of Object Segmentation in Video with Highly Probable Positive Features.- 6. Coupling Appearance and Motion: Unsupervised Clustering for Object Segmentation through Space and Time.- 7. Unsupervised Learning in Space and Time over Several Generations of Teacher and Student Networks.- 8. Unsupervised Learning Towards the Future.
£107.99
Springer Nature Switzerland AG Guide to Intelligent Data Science: How to Intelligently Make Use of Real Data
Book SynopsisMaking use of data is not anymore a niche project but central to almost every project. With access to massive compute resources and vast amounts of data, it seems at least in principle possible to solve any problem. However, successful data science projects result from the intelligent application of: human intuition in combination with computational power; sound background knowledge with computer-aided modelling; and critical reflection of the obtained insights and results.Substantially updating the previous edition, then entitled Guide to Intelligent Data Analysis, this core textbook continues to provide a hands-on instructional approach to many data science techniques, and explains how these are used to solve real world problems. The work balances the practical aspects of applying and using data science techniques with the theoretical and algorithmic underpinnings from mathematics and statistics. Major updates on techniques and subject coverage (including deep learning) are included.Topics and features: guides the reader through the process of data science, following the interdependent steps of project understanding, data understanding, data blending and transformation, modeling, as well as deployment and monitoring; includes numerous examples using the open source KNIME Analytics Platform, together with an introductory appendix; provides a review of the basics of classical statistics that support and justify many data analysis methods, and a glossary of statistical terms; integrates illustrations and case-study-style examples to support pedagogical exposition; supplies further tools and information at an associated website.This practical and systematic textbook/reference is a “need-to-have” tool for graduate and advanced undergraduate students and essential reading for all professionals who face data science problems. Moreover, it is a “need to use, need to keep” resource following one's exploration of the subject.Table of ContentsIntroduction Practical Data Analysis: An Example Project Understanding Data Understanding Principles of Modeling Data Preparation Finding Patterns Finding Explanations Finding Predictors Evaluation and DeploymentThe Labelling Problem Appendix A: Statistics Appendix B: KNIME
£41.70
Springer Nature Switzerland AG Statistical Field Theory for Neural Networks
Book SynopsisThis book presents a self-contained introduction to techniques from field theory applied to stochastic and collective dynamics in neuronal networks. These powerful analytical techniques, which are well established in other fields of physics, are the basis of current developments and offer solutions to pressing open problems in theoretical neuroscience and also machine learning. They enable a systematic and quantitative understanding of the dynamics in recurrent and stochastic neuronal networks. This book is intended for physicists, mathematicians, and computer scientists and it is designed for self-study by researchers who want to enter the field or as the main text for a one semester course at advanced undergraduate or graduate level. The theoretical concepts presented in this book are systematically developed from the very beginning, which only requires basic knowledge of analysis and linear algebra.Table of ContentsI. IntroductionII. Probabilities, moments, cumulantsA. Probabilities, observables, and momentsB. Transformation of random variablesC. CumulantsD. Connection between moments and cumulantsIII. Gaussian distribution and Wick’s theoremA. Gaussian distributionB. Moment and cumulant generating function of a GaussianC. Wick’s theoremD. Graphical representation: Feynman diagramsE. Appendix: Self-adjoint operatorsF. Appendix: Normalization of a GaussianIV. Perturbation expansionA. General caseB. Special case of a Gaussian solvable theoryC. Example: Example: “phi^3 + phi^4” theoryD. External sourcesE. Cancellation of vacuum diagramsF. Equivalence of graphical rules for n-point correlation and n-th momentG. Example: “phi^3 + phi^4” theoryV. Linked cluster theoremA. General proof of the linked cluster theoremB. Dependence on j - external sources - two complimentary viewsC. Example: Connected diagrams of the “phi^3 + phi^4” theoryVI. Functional preliminariesA. Functional derivative1. Product rule2. Chain rule3. Special case of the chain rule: Fourier transformB. Functional Taylor seriesVII. Functional formulation of stochastic differential equationsA. Onsager-Machlup path integral*B. Martin-Siggia-Rose-De Dominicis-Janssen (MSRDJ) path integralC. Moment generating functionalD. Response function in the MSRDJ formalismVIII. Ornstein-Uhlenbeck process: The free Gaussian theoryA. DefinitionB. Propagators in time domainC. Propagators in Fourier domainIX. Perturbation theory for stochastic differential equationsA. Vanishing moments of response fieldsB. Vanishing response loopsC. Feynman rules for SDEs in time domain and frequency domainD. Diagrams with more than a single external legE. Appendix: Unitary Fourier transformX. Dynamic mean-field theory for random networksA. Definition of the model and generating functionalB. Property of self-averagingC. Average over the quenched disorderD. Stationary statistics: Self-consistent autocorrelation of as motion of a particle in a potentialE. Transition to chaosF. Assessing chaos by a pair of identical systemsG. Schrödinger equation for the maximum Lyapunov exponentH. Condition for transition to chaosXI. Vertex generating functionA. Motivating example for the expansion around a non-vanishing mean valueB. Legendre transform and definition of the vertex generating function GammaC. Perturbation expansion of GammaD. Generalized one-line irreducibilityE. ExampleF. Vertex functions in the Gaussian caseG. Example: Vertex functions of the “phi^3 + phi^4”-theoryH. Appendix: Explicit cancellation until second orderI. Appendix: Convexity of WJ. Appendix: Legendre transform of a GaussianXII. Application: TAP approximationInverse problemXIII. Expansion of cumulants into tree diagrams of vertex functionsA. Self-energy or mass operator SigmaXIV. Loopwise expansion of the effective action - Tree levelA. Counting the number of loopsB. Loopwise expansion of the effective action - Higher numbers of loopsC. Example: phi^3 + phi^4-theoryD. Appendix: Equivalence of loopwise expansion and infinite resummationE. Appendix: Interpretation of Gamma as effective actionF. Loopwise expansion of self-consistency equationXV. Loopwise expansion in the MSRDJ formalismA. Intuitive approachB. Loopwise corrections to the effective equation of motionC. Corrections to the self-energy and self-consistencyD. Self-energy correction to the full propagatorE. Self-consistent one-loopF. Appendix: Solution by Fokker-Planck equationXVI. NomenclatureAcknowledgmentsReferences
£56.99
Springer Nature Switzerland AG A Machine Learning based Pairs Trading Investment Strategy
Book Synopsis This book investigates the application of promising machine learning techniques to address two problems: (i) how to find profitable pairs while constraining the search space and (ii) how to avoid long decline periods due to prolonged divergent pairs. It also proposes the integration of an unsupervised learning algorithm, OPTICS, to handle problem (i), and demonstrates that the suggested technique can outperform the common pairs search methods, achieving an average portfolio Sharpe ratio of 3.79, in comparison to 3.58 and 2.59 obtained using standard approaches. For problem (ii), the authors introduce a forecasting-based trading model capable of reducing the periods of portfolio decline by 75%. However, this comes at the expense of decreasing overall profitability. The authors also test the proposed strategy using an ARMA model, an LSTM and an LSTM encoder-decoder.Table of ContentsChapter 1. Introduction Chapter 2. Pairs Trading – Background and Related Work Chapter 3. Proposed Pairs Selection Framework Chapter 4. Proposed Trading Model Chapter 5. Implementation Chapter 6. Results Chapter 7. Conclusions and Future Work
£52.24
Springer Nature Switzerland AG Data Science for Economics and Finance:
Book SynopsisThis open access book covers the use of data science, including advanced machine learning, big data analytics, Semantic Web technologies, natural language processing, social media analysis, time series analysis, among others, for applications in economics and finance. In addition, it shows some successful applications of advanced data science solutions used to extract new knowledge from data in order to improve economic forecasting models. The book starts with an introduction on the use of data science technologies in economics and finance and is followed by thirteen chapters showing success stories of the application of specific data science methodologies, touching on particular topics related to novel big data sources and technologies for economic analysis (e.g. social media and news); big data models leveraging on supervised/unsupervised (deep) machine learning; natural language processing to build economic and financial indicators; and forecasting and nowcasting of economic variables through time series analysis. This book is relevant to all stakeholders involved in digital and data-intensive research in economics and finance, helping them to understand the main opportunities and challenges, become familiar with the latest methodological findings, and learn how to use and evaluate the performances of novel tools and frameworks. It primarily targets data scientists and business analysts exploiting data science technologies, and it will also be a useful resource to research students in disciplines and courses related to these topics. Overall, readers will learn modern and effective data science solutions to create tangible innovations for economic and financial applications. Table of Contents
£31.49
Springer Nature Switzerland AG Artificial Intelligence for Materials Science
Book SynopsisMachine learning methods have lowered the cost of exploring new structures of unknown compounds, and can be used to predict reasonable expectations and subsequently validated by experimental results. As new insights and several elaborative tools have been developed for materials science and engineering in recent years, it is an appropriate time to present a book covering recent progress in this field.Searchable and interactive databases can promote research on emerging materials. Recently, databases containing a large number of high-quality materials properties for new advanced materials discovery have been developed. These approaches are set to make a significant impact on human life and, with numerous commercial developments emerging, will become a major academic topic in the coming years. This authoritative and comprehensive book will be of interest to both existing researchers in this field as well as others in the materials science community who wish to take advantage of these powerful techniques. The book offers a global spread of authors, from USA, Canada, UK, Japan, France, Russia, China and Singapore, who are all world recognized experts in their separate areas. With content relevant to both academic and commercial points of view, and offering an accessible overview of recent progress and potential future directions, the book will interest graduate students, postgraduate researchers, and consultants and industrial engineers.Table of ContentsChapter 1. Materials Genome Initiatives: Past, Present, and Prospect Gang Zhang, Institute of High Performance Computing, A*STAR, 138632 Singapore. zhangg@ihpc.a-star.edu.sg Chapter 2. Introduction of the Machine Learning method Tian Wang, Hichem Snoussi 1. School of Automation Science and Electrical Engineering, Beihang University, Beijing 100083, China. Email: wangtian@buaa.edu.cn 2. Institute Charles Delaunay-LM2S FRE CNRS 2019, University of Technology of Troyes, Troyes 10030, France. Email: hichem.snouss@utt.fr Chapter 3. Machine learning for high entropy alloys Yuan Cheng, Huajian Gao Institute of High Performance Computing, A*STAR, 138632 Singapore; School of Mechanical and Aerospace Engineering, College of Engineering, Nanyang Technological University, 70 Nanyang Drive, Singapore 637457, Singapore. huajian.gao@ntu.edu.sg Chapter 4. Machine learning for biomaterial design Markus J. Buehler, Laboratory for Atomistic and Molecular Mechanics (LAMM), Department of Civil and Environmental Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Room 1-290, Cambridge, Massachusetts 02139, USA. Email: mbuehler@MIT.EDU Chapter 5. Rapid Photovoltaic Device Characterization through AI technology Tonio Buonassisi, MIT. Email: BUONASSISI@MIT.EDU Chapter 6. Machine learning for thermal contact design Junichiro Shiomi, The University of Tokyo, Japan. shiomi@photon.t.u‑tokyo.ac.jp Chapter 7. Discovery of new thermoelectric material through high-throughput calculation Wenqing Zhang, Southern University of Science and Technology, China. zhangwq@sustc.edu.cn Chapter 8. Machine learning for high heat conductive material Eric S. Toberer, Colorado School of Mines, USA. E-mail: etoberer@mines.edu Chapter 9. Machine learning assisted discovery of new 2D Materials Huafeng Dong, Guangdong University of Technology, China. Email: hfdong@gdut.edu.cn. Chapter 10. Interatomic Potentials developed through Machine Learning Lin-Wang Wang, Lawrence Berkeley National Laboratory, Berkeley, USA. Email: lwwang@lbl.gov Chapter 11. Discovery of new Compounds Arthur Mar, Department of Chemistry, University of Alberta, Canada. E-mail: amar@ualberta.ca. Chapter 12. Defect Dynamics Probed by Using Machine Learning and Experiment. Anja Aarva, Aalto University, 02150 Espoo, Finland. E-mail: anja.aarva@aalto.fi. Chapter 13. Machine-Learning Analysis to Predict electronic properties Xi Zhu, The Chinese University of Hong Kong, E-mail: zhuxi@cuhk.edu.cn. Chapter 14. Machine-Learning Analysis to Predict spin properties Dmitry V. Krasnikov, Skolkovo Institute of Science and Technology, Russian Federation. E-mail: d.krasnikov@skoltech.ru. Chapter 15. Determination of Material and Structural Parameters using Two-way Neural Network Xu Han, School of Mechanical Engineering, Hebei University of Technology, Tianjin, 300401, China. E-mail: xhan@hebut.edu.cn
£123.49
Springer Nature Switzerland AG An Intuitive Exploration of Artificial
Book SynopsisThis book develops a conceptual understanding of Artificial Intelligence (AI), Deep Learning and Machine Learning in the truest sense of the word. It is an earnest endeavor to unravel what is happening at the algorithmic level, to grasp how applications are being built and to show the long adventurous road in the future.An Intuitive Exploration of Artificial Intelligence offers insightful details on how AI works and solves problems in computer vision, natural language understanding, speech understanding, reinforcement learning and synthesis of new content. From the classic problem of recognizing cats and dogs, to building autonomous vehicles, to translating text into another language, to automatically converting speech into text and back to speech, to generating neural art, to playing games, and the author's own experience in building solutions in industry, this book is about explaining how exactly the myriad applications of AI flow out of its immense potential.The book is intended to serve as a textbook for graduate and senior-level undergraduate courses in AI. Moreover, since the book provides a strong geometrical intuition about advanced mathematical foundations of AI, practitioners and researchers will equally benefit from the book.Table of ContentsPart I, Foundations.- AI Sculpture.- Make Me Learn.- Images and Sequences.- Why AI Works.- Learning to Sculpt.- Unleashing the Power of Generation.- The Road Most Rewarded.- The Classical World.- Part II, Applications.- To See is to Believe.- Read, Read, Read.- Lend Me Your Ear.- Create Your Shire and Rivendell.- Math to Code to Petaflops.- AI and Business.- Part III, Road Ahead.- Keep Marching on.- Benevolent AI for All.- Am I Looking at Myself?.- App. A, Solutions.- Further Reading.- Acronyms.- Glossary.- References.- Index.
£49.49
Springer Nature Switzerland AG Explainable AI with Python
Book SynopsisThis book provides a full presentation of the current concepts and available techniques to make “machine learning” systems more explainable. The approaches presented can be applied to almost all the current “machine learning” models: linear and logistic regression, deep learning neural networks, natural language processing and image recognition, among the others.Progress in Machine Learning is increasing the use of artificial agents to perform critical tasks previously handled by humans (healthcare, legal and finance, among others). While the principles that guide the design of these agents are understood, most of the current deep-learning models are "opaque" to human understanding. Explainable AI with Python fills the current gap in literature on this emerging topic by taking both a theoretical and a practical perspective, making the reader quickly capable of working with tools and code for Explainable AI.Beginning with examples of what Explainable AI (XAI) is and why it is needed in the field, the book details different approaches to XAI depending on specific context and need. Hands-on work on interpretable models with specific examples leveraging Python are then presented, showing how intrinsic interpretable models can be interpreted and how to produce “human understandable” explanations. Model-agnostic methods for XAI are shown to produce explanations without relying on ML models internals that are “opaque.” Using examples from Computer Vision, the authors then look at explainable models for Deep Learning and prospective methods for the future. Taking a practical perspective, the authors demonstrate how to effectively use ML and XAI in science. The final chapter explains Adversarial Machine Learning and how to do XAI with adversarial examples.Table of ContentsContents1. The Landscape1.1 Examples of what Explainable AI is1.1.1 Learning Phase1.1.2 Knowledge Discovery1.1.3 Reliability and Robustness1.1.4 What have we learnt from the 3 examples1.2 Machine Learning and XAI1.2.1 Machine Learning tassonomy1.2.2 Common Myths1.3 The need for Explainable AI1.4 Explainability and Interpretability: different words to say the same thing or not?1.4.1 From World to Humans1.4.2 Correlation is not causation1.4.3 So what is the difference between interpretability and explainability?1.5 Making Machine Learning systems explainable1.5.1 The XAI flow1.5.2 The big picture1.6 Do we really need to make Machine Learning Models explainable?1.7 Summary1.8 References2. Explainable AI: needs, opportunities and challenges2.1 Human in the loop2.1.1 Centaur XAI systems2.1.2 XAI evaluation from “Human in The Loop perspective”2.2 How to make Machine Learning models explainable2.2.1 Intrinsic Explanations2.2.2 Post-Hoc Explanations2.2.3 Global or Local Explainability2.3 Properties of Explanations2.4 Summary2.5 References3 Intrinsic Explainable Models3.1.Loss Function3.2.Linear Regression3.3.Logistic Regression3.4.Decision Trees3.5.K-Nearest Neighbors (KNN)3.6.Summary3.7 References4. Model-agnostic methods for XAI4.1 Global Explanations: permutation Importance and Partial Dependence Plot4.1.1 Ranking features by Permutation Importance4.1.2 Permutation Importance on the train set4.1.3 Partial Dependence Plot4.1.4 Properties of Explanations4.2 Local Explanations: XAI with Shapley Additive explanations4.2.1 Shapley Values: a game-theoretical approach4.2.2 The first use of SHAP4.2.3 Properties of Explanations4.3 The road to KernelSHAP4.3.1 The Shapley formula4.3.2 How to calculate Shapley values4.3.3 Local Linear Surrogate Models (LIME)4.3.4 KernelSHAP is a unique form of LIME4.4 Kernel SHAP and interactions4.4.1 The NewYork Cab scenario4.4.2 Train the Model with preliminary analysis4.4.3 Making the model explainable with KernelShap4.4.4 Interactions of features4.5 A faster SHAP for boosted trees4.5.1 Using TreeShap4.5.2 Providing explanations4.6 A naïve criticism to SHAP4.7 Summary4.8 References5. Explaining Deep Learning Models5.1 Agnostic Approach5.1.1 Adversarial Features5.1.2 Augmentations5.1.3 Occlusions as augmentations5.1.4 Occlusions as an Agnostic XAI Method5.2 Neural Networks5.2.1 The neural network structure5.2.2 Why the neural network is Deep? (vs shallow)5.2.3 Rectified activations (and Batch Normalization)5.2.4 Saliency Maps5.3 Opening Deep Networks5.3.1 Different layer explanation5.3.2 CAM (Class Activation Maps) and Grad-CAM5.3.3 DeepShap / DeepLift5.4 A critic of Saliency Methods5.4.1 What the network sees5.4.2 Explainability batch normalizing layer by layer5.5 Unsupervised Methods5.5.1 Unsupervised Dimensional Reduction5.5.2 Dimensional reduction of convolutional filters5.5.3 Activation Atlases: How to tell a wok from a pan5.6 Summary5.7 References6. Making science with Machine Learning and XAI6.1 Scientific method in the age of data6.2 Ladder of Causation6.3 Discovering physics concepts with ML and XAI6.3.1 The magic of autoencoders6.3.2 Discover the physics of damped pendulum with ML and XAI6.3.3 Climbing the ladder of causation6.4 Science in the age of ML and XAI6.5 Summary6.6 References7. Adversarial Machine Learning and Explainability7.1 Adversarial Examples (AE) crash course7.1.2 Hands-on Adversarial Examples7.2 Doing XAI with Adversarial Examples7.3 Defending against Adversarial Attacks with XAI7.4 Summary7.5 References8. A proposal for a sustainable model of Explainable AI8.1 The XAI "fil rouge"8.2 XAI and GDPR8.2.1 FAST XAI8.3 Conclusions8.4 Summary8.5 ReferencesIndex
£52.24
Springer Nature Switzerland AG Machine Learning for Engineers: Using data to
Book SynopsisAll engineers and applied scientists will need to harness the power of machine learning to solve the highly complex and data intensive problems now emerging. This text teaches state-of-the-art machine learning technologies to students and practicing engineers from the traditionally “analog” disciplines—mechanical, aerospace, chemical, nuclear, and civil. Dr. McClarren examines these technologies from an engineering perspective and illustrates their specific value to engineers by presenting concrete examples based on physical systems. The book proceeds from basic learning models to deep neural networks, gradually increasing readers’ ability to apply modern machine learning techniques to their current work and to prepare them for future, as yet unknown, problems. Rather than taking a black box approach, the author teaches a broad range of techniques while conveying the kinds of problems best addressed by each. Examples and case studies in controls, dynamics, heat transfer, and other engineering applications are implemented in Python and the libraries scikit-learn and tensorflow, demonstrating how readers can apply the most up-to-date methods to their own problems. The book equally benefits undergraduate engineering students who wish to acquire the skills required by future employers, and practicing engineers who wish to expand and update their problem-solving toolkit.Table of ContentsPart I Fundamentals 1.0 Introduction 1.1. Where machine learning can help engineers 1.2. Where machine learning cannot help engineers 1.3. Machine learning to correct idealized models 2. The Landscape of machine learning 2.1. Supervised learning 2.1.1. Regression 2.1.2. Classification 2.1.3. Time series 2.1.4. Reinforcement 2.2. Unsupervised Learning 2.3. Optimization 2.4. Bayesian statistics 2.5. Cross-validation 3. Linear Models 3.1. Linear regression 3.2. Logistic regression 3.3. Regularized regression 3.4. Case Study: Determining physical laws using regularized regression 4. Tree-Based Models 4.1. Decision Trees 4.2. Random Forests 4.3. BART 4.4. Case Study: Modeling an experiment using random forest models 5. Clustering data 5.1. Singular value decomposition 5.2. Case Study: SVD to standardize several time series 5.3. K-means 5.4. K-nearest neighbors 5.5. t-SNE 5.6. Case Study: The reflectance spectrum of different foliage Part II Deep Neural Networks 6. Feed-Forward Neural Networks 6.1. Neurons 6.2. Dropout 6.3. Backpropagation 6.4. Initialization 6.5. Regression 6.6. Classification 6.7. Case Study: The strength of concrete as a function of age and ingredients 7. Convolutional Neural Networks 7.1. Convolutions 7.2. Pooling 7.3. Residual networks 7.4. Case Study: Finding volcanoes on Venus 8. Recurrent neural networks for time series data 8.1. Basic Recurrent neural networks 8.2. Long-term, Short-Term memory 8.3. Attention networks 8.4. Case Study: Predicting future system performance Part III Advanced Topics in Machine Learning 9. Unsupervised Learning with Neural Networks 9.1. Auto-encoders 9.2. Boltzmann machines 9.3. Case study: Optimization using Inverse models 10. Reinforcement learning 10.1. Case study: controlling a mechanical gantry 11. Transfer learning 11.1. Case study: Transfer learning a simulation emulator for experimental measurements Part IV Appendices A. SciKit-Learn B. Tensorflow
£61.74
Springer Nature Switzerland AG Machine Learning for Engineers: Using data to
Book SynopsisAll engineers and applied scientists will need to harness the power of machine learning to solve the highly complex and data intensive problems now emerging. This text teaches state-of-the-art machine learning technologies to students and practicing engineers from the traditionally “analog” disciplines—mechanical, aerospace, chemical, nuclear, and civil. Dr. McClarren examines these technologies from an engineering perspective and illustrates their specific value to engineers by presenting concrete examples based on physical systems. The book proceeds from basic learning models to deep neural networks, gradually increasing readers’ ability to apply modern machine learning techniques to their current work and to prepare them for future, as yet unknown, problems. Rather than taking a black box approach, the author teaches a broad range of techniques while conveying the kinds of problems best addressed by each. Examples and case studies in controls, dynamics, heat transfer, and other engineering applications are implemented in Python and the libraries scikit-learn and tensorflow, demonstrating how readers can apply the most up-to-date methods to their own problems. The book equally benefits undergraduate engineering students who wish to acquire the skills required by future employers, and practicing engineers who wish to expand and update their problem-solving toolkit.Table of ContentsPart I Fundamentals 1.0 Introduction 1.1. Where machine learning can help engineers 1.2. Where machine learning cannot help engineers 1.3. Machine learning to correct idealized models 2. The Landscape of machine learning 2.1. Supervised learning 2.1.1. Regression 2.1.2. Classification 2.1.3. Time series 2.1.4. Reinforcement 2.2. Unsupervised Learning 2.3. Optimization 2.4. Bayesian statistics 2.5. Cross-validation 3. Linear Models 3.1. Linear regression 3.2. Logistic regression 3.3. Regularized regression 3.4. Case Study: Determining physical laws using regularized regression 4. Tree-Based Models 4.1. Decision Trees 4.2. Random Forests 4.3. BART 4.4. Case Study: Modeling an experiment using random forest models 5. Clustering data 5.1. Singular value decomposition 5.2. Case Study: SVD to standardize several time series 5.3. K-means 5.4. K-nearest neighbors 5.5. t-SNE 5.6. Case Study: The reflectance spectrum of different foliage Part II Deep Neural Networks 6. Feed-Forward Neural Networks 6.1. Neurons 6.2. Dropout 6.3. Backpropagation 6.4. Initialization 6.5. Regression 6.6. Classification 6.7. Case Study: The strength of concrete as a function of age and ingredients 7. Convolutional Neural Networks 7.1. Convolutions 7.2. Pooling 7.3. Residual networks 7.4. Case Study: Finding volcanoes on Venus 8. Recurrent neural networks for time series data 8.1. Basic Recurrent neural networks 8.2. Long-term, Short-Term memory 8.3. Attention networks 8.4. Case Study: Predicting future system performance Part III Advanced Topics in Machine Learning 9. Unsupervised Learning with Neural Networks 9.1. Auto-encoders 9.2. Boltzmann machines 9.3. Case study: Optimization using Inverse models 10. Reinforcement learning 10.1. Case study: controlling a mechanical gantry 11. Transfer learning 11.1. Case study: Transfer learning a simulation emulator for experimental measurements Part IV Appendices A. SciKit-Learn B. Tensorflow
£47.49
Springer Nature Switzerland AG Metaheuristics in Machine Learning: Theory and
Book SynopsisThis book is a collection of the most recent approaches that combine metaheuristics and machine learning. Some of the methods considered in this book are evolutionary, swarm, machine learning, and deep learning. The chapters were classified based on the content; then, the sections are thematic. Different applications and implementations are included; in this sense, the book provides theory and practical content with novel machine learning and metaheuristic algorithms.The chapters were compiled using a scientific perspective. Accordingly, the book is primarily intended for undergraduate and postgraduate students of Science, Engineering, and Computational Mathematics and is useful in courses on Artificial Intelligence, Advanced Machine Learning, among others. Likewise, the book is useful for research from the evolutionary computation, artificial intelligence, and image processing communities. Table of ContentsCross Entropy Based Thresholding Segmentation of Magnetic Resonance Prostatic Images Using Metaheuristic Algorithms.- Hyperparameter Optimization in a Convolutional Neural Network Using Metaheuristic Algorithms.- Diagnosis of collateral effects in climate change through the identification of leaf damage using a novel heuristics and machine learning framework.- Feature engineering for Machine Learning and Deep Learning assisted Wireless Communication.- Genetic operators and their impact on the training of deep neural networks.- Implementation of metaheuristics with Extreme Learning Machines.- Architecture optimization of convolutional neural networks by micro genetic algorithms.- Optimising Connection Weights in Neural Networks using a Memetic Algorithm Incorporating Chaos Theory.- A review of metaheuristic optimization algorithms for wireless sensor networks.- A Metaheuristic Algorithm for Classification of White Blood Cells in Healthcare Informatics.- A Review of multi-level thresholding image segmentation using nature-inspired optimization algorithms.- Hybrid Harris Hawks Optimization with Differential Evolution for Data Clustering.- Variable Mesh Optimization for Continuous Optimization and Multimodal Problems.- Traffic control using image processing and deep learning techniques.- Drug Design and Discovery: Theory,Applications, Open Issues and Challenges.- Thresholding algorithm applied to Chest X-Ray images with Pneumonia.- Artificial neural networks for stock market prediction: a comprehensive review.- Image classification with Convolutional Neural Networks.- Applied Machine Learning Techniques to Find Patterns and Trends in the Use of Bicycle Sharing Systems Influenced by Traffic Accidents and Violent Events in Guadalajara, Mexico.- Machine Reading Comprehension (LSTM) Review (state of art).- A Survey of Metaheuristic Algorithms for Solving Optimization Problems.- Integrating metaheuristic algorithms and minimum cross entropy for image segmentation in mist conditions.- A Machine Learning application for Particle Physics: Mexico’s involvement in the Hyper- Kamiokande observatory.- A novel metaheuristic approach for Image Contrast Enhancement based on gray-scale mapping.- Geospatial Data Mining Techniques Survey.- Integration of Internet of Things and cloud computing for Cardiac health recognition.- Combinatorial Optimization for Artificial Intelligence Enabled Mobile Network Automation.- Performance Optimization of PID Controller based on Parameters Estimation using Meta-Heuristic Techniques : A Comparative Study.- Solar Irradiation Changes Detection for Photovoltaic Systems through ANN trained with a Metaheuristic Algorithm.- Genetic Algorithm based Global and Local Feature Selection Approach for Handwritten Numeral Recognition.
£125.99
Springer Nature Switzerland AG Decision Economics: Minds, Machines, and their
Book SynopsisThis book is the result of a multi-year research project led and sponsored by the University of Chieti-Pescara, National Chengchi University, University of Salamanca, and Osaka University. It is the fifth volume to emerge from that international project, held under the aegis of the United Nations Academic Impact in 2020. All the essays in this volume were (virtually) discussed at the University of L’Aquila―as the venue of the 2nd International Conference on Decision Economics, a three-day global gathering of approximately one hundred scholars and practitioners—and were subjected to thorough peer review by leading experts in the field. The essays reflect the extent, diversity, and richness of several research areas, both normative and descriptive, and are an invaluable resource for graduate-level and PhD students, academics, researchers, policymakers and other professionals, especially in the social and cognitive sciences. Given its interdisciplinary scope, the book subsequently delivers new approaches on how to contribute to the future of economics, providing alternative explanations for various socio-economic issues such as computable humanities; cognitive, behavioural, and experimental perspectives in economics; data analysis and machine learning as well as research areas at the intersection of computer science, artificial intelligence, mathematics, and statistics; agent-based modelling and the related. The editors are grateful to the scientific committee for its continuous support throughout the research project as well as to the many participants for their insightful comments and always probing questions. In any case, the collaboration involved in the project extends far beyond the group of authors published in this volume and is reflected in the quality of the essays published over the years.
£151.99
Springer Nature Switzerland AG Artificial Intelligence and Machine Learning: 32nd Benelux Conference, BNAIC/Benelearn 2020, Leiden, The Netherlands, November 19–20, 2020, Revised Selected Papers
Book SynopsisThis book contains a selection of the best papers of the 32nd Benelux Conference on Artificial Intelligence, BNAIC/Benelearn 2020, held in Leiden, The Netherlands, in November 2020. Due to the COVID-19 pandemic the conference was held online. The 12 papers presented in this volume were carefully reviewed and selected from 41 regular submissions. They address various aspects of artificial intelligence such as natural language processing, agent technology, game theory, problem solving, machine learning, human-agent interaction, AI and education, and data analysis.The chapter 11 is published open access under a CC BY license (Creative Commons Attribution 4.0 International License) Chapter “Gaining Insight into Determinants of Physical Activity Using Bayesian Network Learning” is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.. Table of ContentsEvaluating the Robustness of Question-Answering Models to Paraphrased Questions.- FlipOut: Uncovering Redundant Weights via Sign Flipping.- Evolving Virtual Embodied Agents using External Artifact Evaluations.- Continuous Surrogate-based Optimization Algorithms are Well-suitedfor Expensive Discrete Problems.- Comparing Correction Methods to Reduce Misclassification Bias.- A Spiking Neuron Implementation of Genetic Algorithms for Optimization.- Solving Hofstadter's Analogies using Structural Information Theory.- A Semantic Tableau Method for Argument Construction.- `Thy algorithm shalt not bear false witness': An Evaluation of Multiclass Debiasing Methods on Word Embeddings.- An Intelligent Tree Planning Approach using Location-based Social Networks Data.- Gaining Insight into Determinants of Physical Activity using Bayesian Network Learning.- Swarm Construction Coordinated through the Building Material.
£49.49
Springer Nature Switzerland AG Introduction to Deep Learning for Healthcare
Book SynopsisThis textbook presents deep learning models and their healthcare applications. It focuses on rich health data and deep learning models that can effectively model health data. Healthcare data: Among all healthcare technologies, electronic health records (EHRs) had vast adoption and a significant impact on healthcare delivery in recent years. One crucial benefit of EHRs is to capture all the patient encounters with rich multi-modality data. Healthcare data include both structured and unstructured information. Structured data include various medical codes for diagnoses and procedures, lab results, and medication information. Unstructured data contain 1) clinical notes as text, 2) medical imaging data such as X-rays, echocardiogram, and magnetic resonance imaging (MRI), and 3) time-series data such as the electrocardiogram (ECG) and electroencephalogram (EEG). Beyond the data collected during clinical visits, patient self-generated/reported data start to grow thanks to wearable sensors’ increasing use. The authors present deep learning case studies on all data described.Deep learning models: Neural network models are a class of machine learning methods with a long history. Deep learning models are neural networks of many layers, which can extract multiple levels of features from raw data. Deep learning applied to healthcare is a natural and promising direction with many initial successes. The authors cover deep neural networks, convolutional neural networks, recurrent neural networks, embedding methods, autoencoders, attention models, graph neural networks, memory networks, and generative models. It’s presented with concrete healthcare case studies such as clinical predictive modeling, readmission prediction, phenotyping, x-ray classification, ECG diagnosis, sleep monitoring, automatic diagnosis coding from clinical notes, automatic deidentification, medication recommendation, drug discovery (drug property prediction and molecule generation), and clinical trial matching.This textbook targets graduate-level students focused on deep learning methods and their healthcare applications. It can be used for the concepts of deep learning and its applications as well. Researchers working in this field will also find this book to be extremely useful and valuable for their research.Table of ContentsContentsI IntroductionI.1 Who should read this book?I.2 Book organizationII Health DataII.1 The growth of EHR AdoptionII.2 Health DataII.2.1 Life cycle of health dataII.2.2 Structured Health DataII.2.3 Unstructured clinical notesII.2.4 Continuous signalsII.2.5 Medical Imaging DataII.2.6 Biomedical data for in silico drug Discovery II.3 Health Data StandardsIII Machine Learning BasicsIII.1 Supervised LearningIII.1.1 Logistic RegressionIII.1.2 Softmax RegressionIII.1.3 Gradient DescentIII.1.4 Stochastic and Minibatch Gradient DescentIII.2 Unsupervised LearningIII.2.1 Principal component analysisIII.2.2 t-distributed stochastic neighbor embedding (t-SNE)III.2.3 ClusteringIII.3 Assessing Model PerformanceIII.3.1 Evaluation Metrics for Regression TasksIII.3.2 Evaluation Metrics for Classification TasksIII.3.3 Evaluation Metrics for Clustering TasksIII.3.4 Evaluation StrategyIII.4 Modeling ExerciseIII.5 Hands-On Practice34 CONTENTSIVDeep Neural Networks (DNN)IV.1 A Single neuronIV.1.1 Activation functionIV.1.2 Loss FunctionIV.1.3 Train a single neuronIV.2 Multilayer Neural NetworkIV.2.1 Network RepresentationIV.2.2 Train a Multilayer Neural NetworkIV.2.3 Summary of the Backpropagation AlgorithmIV.2.4 Parameters and Hyper-parametersIV.3 Readmission Prediction from EHR Data with DNNIV.4 DNN for Drug Property PredictionV EmbeddingV.1 OverviewV.2 Word2VecV.2.1 Idea and Formulation of Word2VecV.2.2 Healthcare application of Word2VecV.3 Med2Vec: two-level embedding for EHRV.3.1 Med2Vec MethodV.4 MiME: Embed Internal StructureV.4.1 Notations of MIMEV.4.2 Description of MIMEV.4.3 Experiment results of MIMEVI Convolutional Neural Networks (CNN)VI.1 CNN intuitionVI.2 Architecture of CNNVI.2.1 Convolution layer - 1DVI.2.2 Convolution layer - 2DVI.2.3 Pooling LayerVI.2.4 Fully Connected LayerVI.3 Backpropagation Algorithm in CNN*VI.3.1 Forward and Backward Computation for 1-D DataVI.3.2 Forward Computation and Backpropagation for 2-D ConvolutionLayer . VI.3.3 Special CNN ArchitectureVI.4 Healthcare Applications VI.5 Automated surveillance of cranial images for acute neurologic eventsVI.6 Detection of Lymph Node Metastases from Pathology ImagesVI.7 Cardiologist-level arrhythmia detection and classification in ambulatoryECGCONTENTS 5VIIRecurrent Neural Networks (RNN)VII.1Basic Concepts and NotationsVII.2Backpropagation Through Time (BPTT) algorithmVII.2.1Forward PassVII.2.2 Backward PassVII.3RNN VariantsVII.3.1 Long Short-Term Memory (LSTM)VII.3.2 Gated Recurrent Unit (GRU)VII.3.3 Bidirectional RNNVII.3.4 Encoder-Decoder Sequence-to-Sequence ModelsVII.4Case Study: Early detection of heart failureVII.5Case Study: Sequential clinical event predictionVII.6Case Study: De-identification of Clinical NotesVII.7Case Study: Automatic Detection of Heart Disease from electrocardiography(ECG) DataVIIAIutoencoders (AE)VIII.1OverviewVIII.2AutoencodersVIII.3Sparse AutoencodersVIII.4Stacked AutoencodersVIII.5Denoising AutoencodersVIII.6Case Study: “Deep Patient” via stacked denoising autoencodersVIII.7Case Study: Learning from Noisy, Sparse, and Irregular ClinicaldataIX Attention ModelsIX.1 OverviewIX.2 Attention MechanismIX.2.1 Attention based on Encoder-Decoder RNN ModelsIX.2.2 Case Study: Attention Model over Longitudinal EHRIX.2.3 Case Study: Attention model over a Medical OntologyIX.2.4 Case Study: ICD Classification from Clinical NotesX Memory NetworksX.1 Original Memory NetworksX.2 End-to-end Memory NetworksX.3 Case Study: Medication RecommendationX.4 EEG-RelNet: Memory Derived from DataX.5 Incorporate Memory from Unstructured Knowledge BaseXIGraph Neural NetworksXI.1 OverviewXI.2 Graph Convolutional NetworksXI.2.1 Basic Setting of GCNXI.2.2 Spatial Convolution on Graphs6 CONTENTSXI.2.3 Spectral Convolution on GraphsXI.2.4 Approximate Graph ConvolutionXI.2.5 Neighborhood AggregationXI.3 Neural Fingerprinting: Drug Molecule Embedding with GCNXI.4 Decagon: Modeling Polypharmacy Side Effects with GCNXI.5 Case Study: Multiview Drug-drug Interaction PredictionXIIGenerative ModelsXII.1Generative adversarial networks (GAN)XII.1.1 The GAN FrameworkXII.1.2 The Cost Function of DiscriminatorXII.1.3 The Cost Function of GeneratorXII.2Variational Autoencoders (VAE)XII.2.1 Latent Variable ModelsXII.2.2Objective FormulationXII.2.3Objective ApproximationXII.2.4 Reparameterization TrickXII.3Case Study: Generating Patient RecordsXII.4Case Study: Small Molecule Generation for Drug DiscoveryXII CIonclusionXIII.1Model SetupXIII.2Model TrainingXIII.3Testing and Performance EvaluationXIII.4Result VisualizationXIII.5Case StudiesXIVAppendixXIV.1Regularization*XIV.1.1Vanishing or Exploding Gradient ProblemXIV.1.2DropoutXIV.1.3Batch normalizationXIV.2Stochastic Gradient Descent and Minibatch gradient descent*XIV.3Advanced optimization*XIV.3.1MomentumXIV.3.2Adagrad, Adadelta, and RMSpropXIV.3.3Adam
£52.24
