Machine learning Books

Book SynopsisFascinating' Greta ThunbergExtraordinary' Merlin SheldrakeA must-read' New ScientistEnthralling' George MonbiotBrilliant' Philip HoareWildlife filmmaker Tom Mustill had always liked whales. But when one breached onto his kayak, nearly killing him, he became obsessed.This book traces his extraordinary investigation into the deep ocean and the cutting-edge science of animal translation.What would it take to speak with a whale? Are we ready for what they might say?MORE PRAISE FOR HOW TO SPEAK WHALEOne of the most exciting and hopeful books I have read in ages' SY MONTGOMERY, AUTHOR OF THE SOUL OF AN OCTOPUSA narrative that will expand your concept of language and deepen your understanding of the many ways there are to be alive It left me inspired' MERLIN SHELDRAKE, AUTHOR OF ENTANGLED LIFEA must-read a hugely engaging personal story of a journey into the future of human-animal communication facilitated by delving into its past' NEW SCIENTISTFascinating and deeply humane' GRETA THUNBERGATrade Review‘A rich exploration of some of the world's most astonishing creatures … Mustill weaves a narrative that will expand your concept of language and deepen your understanding of the many ways there are to be alive. This is an extraordinary book that left me inspired’ Merlin Sheldrake, author of Entangled Life ‘A must-read… a hugely engaging personal story of a journey into the future of human-animal communication facilitated by delving into its past’ New Scientist ‘[An] extensively researched and energetic book… it is via the informed, far-reaching empathy of intermediaries such as Mustill that we stand our best chance of seeing into the non-human depths’ New Statesman ‘First-class … Reasoned, entertaining, and fact-filled’ Forbes ‘Fascinating and deeply humane’ Greta Thunberg ‘A rich, enthralling, brilliant book that opens our eyes and ears to worlds we can scarcely imagine’George Monbiot, Sunday Times bestselling author of Regenesis ‘Tantalizing … Think how transformative it would be if we could chat with whales about their love lives or their sorrows or their thoughts on the philosophy of language’ Elizabeth Kolbert, New Yorker ‘Mind-blowing … You will never feel closer to the magnificence of whales’Lucy Jones, author of Losing Eden ‘A scary, important and brilliant book … If we do get to translate ‘whale’, will we like what they’ve got to say?’Philip Hoare, author of Leviathan ‘Mustill takes us farther, much farther, than Dr. Dolittle ever imagined’ Carl Safina ‘Riveting … One of the most exciting and hopeful books I have read in ages’ Sy Montgomery, author of The Soul of an Octopus ‘Mustill conveys the richness of whale song and communication’ Frans de Waal ‘Lively and informative’ Jonathan Slaght, author of Owls of the Eastern Ice ‘Extraordinary’ Christiana Figueres

Read more less

Book SynopsisSometime in the future the intelligence of machines will exceed that of human brain power. So are we on the edge of an AI-pocalypse, with superintelligent devices superseding humanity, as predicted by Stephen Hawking? Or will this herald a kind of Utopia, with machines doing a far better job at complex tasks than us? You might not realise it, but you interact with AIs every day. They route your phone calls, approve your credit card transactions and help your doctor interpret results. Driverless cars will soon be on the roads with a decision-making computer in charge. But how do machines actually think and learn? In Machines That Think, AI experts and New Scientist explore how artificial intelligence helps us understand human intelligence, machines that compose music and write stories - and ask if AI is really a threat.ABOUT THE SERIESNew Scientist Instant Expert books are definitive and accessible entry points to the most important subjects in science; subjects that challenge, attract debate, invite controversy and engage the most enquiring minds. Designed for curious readers who want to know how things work and why, the Instant Expert series explores the topics that really matter and their impact on individuals, society, and the planet, translating the scientific complexities around us into language that's open to everyone, and putting new ideas and discoveries into perspective and context.

Read more less

Book Synopsis'Absorbing, mind-enlarging, studded with insights ... This could have significant real-world results' Sunday Times Humanity's greatest feat is our incredible ability to learn. Even in their first year, infants acquire language, visual and social knowledge at a rate that surpasses the best supercomputers. But how, exactly, do our brains learn? In How We Learn, leading neuroscientist Stanislas Dehaene delves into the psychological, neuronal, synaptic and molecular mechanisms of learning. Drawing on case studies of children who learned despite huge difficulty and trauma, he explains why youth is such a sensitive period, during which brain plasticity is maximal, but also assures us that our abilities continue into adulthood. We can all enhance our learning and memory at any age and 'learn to learn' by taking maximal advantage of the four pillars of the brain's learning algorithm: attention, active engagement, error feedback and consolidation. The human braiTrade ReviewThis is an absorbing, mind-enlarging book, studded with insights ... Could have significant real-world results. -- James McConnachie * Sunday Times *An entertaining survey of how science from brain scans to psychological tests is helping inspire pedagogy. Dehaene challenges many tropes [and] describes much of his own pioneering work ... Well translated from the French with some touching references to his upbringing, from the cult film La Jetée to the writing of Daniel Pennac. -- Andrew Jack * Financial Times *An expert overview of learning ... Dehaene's fourth insightful exploration of neuroscience will pay dividends for attentive readers. * Kirkus *

Read more less

Book SynopsisThis seminal book injects the topic of superintelligence into the academic and popular mainstream. What happens when machines surpass humans in general intelligence? Will artificial agents save or destroy us? In a tour de force of analytic thinking, Bostrom lays a foundation for understanding the future of humanity and intelligent life.Trade ReviewWorth reading. * Elon Musk, Founder of SpaceX and Tesla *I highly recommend this book * Bill Gates *very deep ... every paragraph has like six ideas embedded within it. * Nate Silver *Nick Bostrom makes a persuasive case that the future impact of AI is perhaps the most important issue the human race has ever faced. Instead of passively drifting, we need to steer a course. Superintelligence charts the submerged rocks of the future with unprecedented detail. It marks the beginning of a new era * Stuart Russell, Professor of Computer Science, University of California, Berkley *Those disposed to dismiss an 'AI takeover' as science fiction may think again after reading this original and well-argued book * Martin Rees, Past President, Royal Society *This superb analysis by one of the worlds clearest thinkers tackles one of humanitys greatest challenges: if future superhuman artificial intelligence becomes the biggest event in human history, then how can we ensure that it doesnt become the last? * Max Tegmark, Professor of Physics, MIT *Terribly important ... groundbreaking... extraordinary sagacity and clarity, enabling him to combine his wide-ranging knowledge over an impressively broad spectrum of disciplines - engineering, natural sciences, medicine, social sciences and philosophy - into a comprehensible whole... If this book gets the reception that it deserves, it may turn out the most important alarm bell since Rachel Carson's Silent Spring from 1962, or ever * Olle Haggstrom, Professor of Mathematical Statistics *Valuable. The implications of introducing a second intelligent species onto Earth are far-reaching enough to deserve hard thinking * The Economist *There is no doubting the force of [Bostrom's] arguments the problem is a research challenge worthy of the next generations best mathematical talent. Human civilisation is at stake * Financial Times *His book Superintelligence: Paths, Dangers, Strategies became an improbable bestseller in 2014 * Alex Massie, Times (Scotland) *Ein Text so nüchtern und cool, so angstfrei und dadurch umso erregender, dass danach das, was bisher vor allem Filme durchgespielt haben, auf einmal höchst plausibel erscheint. A text so sober and cool, so fearless and thus all the more exciting that what has until now mostly been acted through in films, all of a sudden appears most plausible afterwards. (translated from German) * Georg Diez, DER SPIEGEL *Worth reading.... We need to be super careful with AI. Potentially more dangerous than nukes * Elon Musk, Founder of SpaceX and Tesla *A damn hard read * Sunday Telegraph *I recommend Superintelligence by Nick Bostrom as an excellent book on this topic * Jolyon Brown, Linux Format *Every intelligent person should read it. * Nils Nilsson, Artificial Intelligence Pioneer, Stanford University *An intriguing mix of analytic philosophy, computer science and cutting-edge science fiction, Nick Bostrom's Superintelligence is required reading for anyone seeking to make sense of the recent surge of interest in artificial intelligence (AI). * Colin Garvey, Icon *Table of ContentsPreface 1: Past Developments and Present Capabilities 2: Roads to Superintelligence 3: Forms of Superintelligence 4: Singularity Dynamics 5: Decisive Strategic Advantage 6: Intellectual Superpowers 7: The Superintelligent Will 8: Is the Default Outcome Doom? 9: The Control Problem 10: Oracles, Genies, Sovereigns, Tools 11: Multipolar Scenarios 12: Acquiring Values 13: Design Choices 14: The Strategic Picture 15: Nut-Cutting Time Afterword

Read more less

Book SynopsisThis seminal book injects the topic of superintelligence into the academic and popular mainstream. What happens when machines surpass humans in general intelligence? Will artificial agents save or destroy us? In a tour de force of analytic thinking, Bostrom lays a foundation for understanding the future of humanity and intelligent life.Trade ReviewWorth reading. * Elon Musk, Founder of SpaceX and Tesla *I highly recommend this book * Bill Gates *very deep ... every paragraph has like six ideas embedded within it. * Nate Silver *Nick Bostrom makes a persuasive case that the future impact of AI is perhaps the most important issue the human race has ever faced. Instead of passively drifting, we need to steer a course. Superintelligence charts the submerged rocks of the future with unprecedented detail. It marks the beginning of a new era * Stuart Russell, Professor of Computer Science, University of California, Berkley *Those disposed to dismiss an 'AI takeover' as science fiction may think again after reading this original and well-argued book * Martin Rees, Past President, Royal Society *This superb analysis by one of the worlds clearest thinkers tackles one of humanitys greatest challenges: if future superhuman artificial intelligence becomes the biggest event in human history, then how can we ensure that it doesnt become the last? * Max Tegmark, Professor of Physics, MIT *Terribly important ... groundbreaking... extraordinary sagacity and clarity, enabling him to combine his wide-ranging knowledge over an impressively broad spectrum of disciplines - engineering, natural sciences, medicine, social sciences and philosophy - into a comprehensible whole... If this book gets the reception that it deserves, it may turn out the most important alarm bell since Rachel Carson's Silent Spring from 1962, or ever * Olle Haggstrom, Professor of Mathematical Statistics *Valuable. The implications of introducing a second intelligent species onto Earth are far-reaching enough to deserve hard thinking * The Economist *There is no doubting the force of [Bostroms] arguments the problem is a research challenge worthy of the next generations best mathematical talent. Human civilisation is at stake * Financial Times *His book Superintelligence: Paths, Dangers, Strategies became an improbable bestseller in 2014 * Alex Massie, Times (Scotland) *Ein Text so nüchtern und cool, so angstfrei und dadurch umso erregender, dass danach das, was bisher vor allem Filme durchgespielt haben, auf einmal höchst plausibel erscheint. A text so sober and cool, so fearless and thus all the more exciting that what has until now mostly been acted through in films, all of a sudden appears most plausible afterwards. (translated from German) * Georg Diez, DER SPIEGEL *Worth reading.... We need to be super careful with AI. Potentially more dangerous than nukes * Elon Musk, Founder of SpaceX and Tesla *A damn hard read * Sunday Telegraph *I recommend Superintelligence by Nick Bostrom as an excellent book on this topic * Jolyon Brown, Linux Format *Every intelligent person should read it. * Nils Nilsson, Artificial Intelligence Pioneer, Stanford University *An intriguing mix of analytic philosophy, computer science and cutting-edge science fiction, Nick Bostrom's Superintelligence is required reading for anyone seeking to make sense of the recent surge of interest in artificial intelligence (AI). * Colin Garvey, Icon *Table of ContentsPreface ; 1. Past Developments and Present Capabilities ; 2. Roads to Superintelligence ; 3. Forms of Superintelligence ; 4. Singularity Dynamics ; 5. Decisive Strategic Advantage ; 6. Intellectual Superpowers ; 7. The Superintelligent Will ; 8. Is the Default Outcome Doom? ; 9. The Control Problem ; 10. Oracles, Genies, Sovereigns, Tools ; 11. Multipolar Scenarios ; 12. Acquiring Values ; 13. Design Choices ; 14. The Strategic Picture ; 15. Nut-Cutting Time

Read more less

Book Synopsis

Read more less

Book SynopsisAn argument in favor of finding a place for humans (and humanness) in the future digital economy.In the digital economy, accountants, baristas, and cashiers can be automated out of employment; so can surgeons, airline pilots, and cab drivers. Machines will be able to do these jobs more efficiently, accurately, and inexpensively. But, Nicholas Agar warns in this provocative book, these developments could result in a radically disempowered humanity.The digital revolution has brought us new gadgets and new things to do with them. The digital revolution also brings the digital economy, with machines capable of doing humans' jobs. Agar explains that developments in artificial intelligence enable computers to take over not just routine tasks but also the kind of “mind work” that previously relied on human intellect, and that this threatens human agency. The solution, Agar argues, is a hybrid social-digital economy. The key value of the digital economy is efficien

Read more less

Book SynopsisA project-based guide to the basics of deep learning.This concise, project-driven guide to deep learning takes readers through a series of program-writing tasks that introduce them to the use of deep learning in such areas of artificial intelligence as computer vision, natural-language processing, and reinforcement learning. The author, a longtime artificial intelligence researcher specializing in natural-language processing, covers feed-forward neural nets, convolutional neural nets, word embeddings, recurrent neural nets, sequence-to-sequence learning, deep reinforcement learning, unsupervised models, and other fundamental concepts and techniques. Students and practitioners learn the basics of deep learning by working through programs in Tensorflow, an open-source machine learning framework. “I find I learn computer science material best by sitting down and writing programs,” the author writes, and the book reflects this approach.Each chapter includes a p

Read more less

Book SynopsisHow to develop robots that will be more like humans and less like computers, more social than machine-like, and more playful and less programmed.Most robots are not very friendly. They vacuum the rug, mow the lawn, dispose of bombs, even perform surgery—but they aren't good conversationalists. It's difficult to make eye contact. If the future promises more human-robot collaboration in both work and play, wouldn't it be better if the robots were less mechanical and more social? In How to Grow a Robot, Mark Lee explores how robots can be more human-like, friendly, and engaging.Developments in artificial intelligence—notably Deep Learning—are widely seen as the foundation on which our robot future will be built. These advances have already brought us self-driving cars and chess match-winning algorithms. But, Lee writes, we need robots that are perceptive, animated, and responsive—more like humans and less like computers, more social than mac

Read more less

Book SynopsisA clear-eyed look at how AI can complement (rather than eliminate) human jobs, with real-world examples from companies that range from Netflix to Walmart.Descriptions of AI's possible effects on businesses and their employees cycle between utopian hype and alarmist doomsaying. This book from MIT Sloan Management Review avoids both these extremes, providing instead a clear-eyed look at how AI can complement (rather than eliminate) human jobs, with real-world examples from companies that range from Netflix to Walmart. The contributors show that organizations can create business value with AI by cooperating with it rather than relinquishing control to it. The smartest companies know that they don't need AI that mimics humans because they already have access to resources with human capability—actual humans.The book acknowledges the prominent role of such leading technology companies as Facebook, Apple, Amazon, Netflix, and Google in applying AI to their busine

Read more less

Book SynopsisA hands-on textbook teaching how to carry out large-scale data analytics and implement machine learning solutions for big data. Including copious real-world examples, it offers a coherent teaching package with lab assignments, exercises, solutions for instructors, and lecture slides.Trade Review'With the growing ubiquity of large and complex datasets, MapReduce and Spark's dataflow programming models have become mission-critical skills for data scientists, data engineers, and ML engineers. Triguero and Galar leverage their extensive teaching experience on this topic to deliver this tour de force deep dive into both the technical concepts and programming knowhow needed for such modern large-scale data analytics. They interleave intuitive exposition of the concepts and examples from data engineering and classical ML pipelines with well-thought-out hands-on code and outputs. This book not only shows how all this knowledge is useful in practice today but also sets up the reader to be able to successfully 'generalize' to future workloads.' Arun Kumar, University of California, San DiegoTable of ContentsPart I. Understanding and Dealing with Big Data: 1. Introduction; 2. MapReduce; Part II. Big Data Frameworks: 3. Hadoop; 4. Spark; 5. Spark SQL and DataFrames; Part III. Machine Learning for Big Data: 6. Machine Learning with Spark; 7. Machine Learning for Big Data; 8. Implementing Classical Methods: k-means and Linear Regression; 9. Advanced Examples: Semi-supervised, Ensembles, Deep Learning Model Deployment.

Read more less

Book SynopsisThis textbook introduces fundamental concepts, major models, and popular applications of pattern recognition for a one-semester undergraduate course. To ensure student understanding, the text focuses on a relatively small number of core concepts with an abundance of illustrations and examples. Concepts are reinforced with hands-on exercises to nurture the student''s skill in problem solving. New concepts and algorithms are framed by real-world context and established as part of the big picture introduced in an early chapter. A problem-solving strategy is employed in several chapters to equip students with an approach for new problems in pattern recognition. This text also points out common errors that a new player in pattern recognition may encounter, and fosters the ability for readers to find useful resources and independently solve a new pattern recognition task through various working examples. Students with an undergraduate understanding of mathematical analysis, linear algebra, and probability will be well prepared to master the concepts and mathematical analysis presented here.Trade Review'I highly recommend this book to all those computer-science students who mainly focus on deep learning: this is the book they should read, where they can learn the fundamentals and the big picture of pattern recognition, which will benefit them in the long run.' Jianfei Cai, Monash University'Dr. Wu has written a valuable book that could not be more timely: the commoditization of machine learning is putting increasingly powerful tools for working with data in the hands of an increasingly broad population of users and practitioners. However, using these tools correctly and interpreting their outputs properly still require significant expertise. This book fills the gap between the classic pattern-recognition texts that assume a substantial amount of background knowledge and preparation and the innumerable internet blog posts which are highly accessible but often superficial. I am sure this self-contained and useful book will enjoy widespread adoption, and I recommend it highly.' James M. Rehg, Georgia Institute of Technology'This well-designed book is both accessible and substantial in content. I highly recommend it as a textbook as well as for self-study.' Zhi-Hua Zhou, Nanjing UniversityTable of ContentsPreface; Notation; Part I. Introduction and Overview: 1. Introduction; 2. Mathematical background; 3. Overview of a pattern recognition system; 4. Evaluation; Part II. Domain-Independent Feature Extraction: 5. Principal component analysis; 6. Fisher's linear discriminant; Part III. Classifiers and Tools: 7. Support vector machines; 8. Probabilistic methods; 9. Distance metrics and data transformations; 10. Information theory and decision trees; Part IV. Handling Diverse Data Formats: 11. Sparse and misaligned data; 12. Hidden Markov model; Part V. Advanced Topics: 13. The normal distribution; 14. The basic idea behind expectation-maximization; 15. Convolutional neural networks; References; Index.

Read more less

Book SynopsisThe twenty-first century has seen a breathtaking expansion of statistical methodology, both in scope and influence. ''Data science'' and ''machine learning'' have become familiar terms in the news, as statistical methods are brought to bear upon the enormous data sets of modern science and commerce. How did we get here? And where are we going? How does it all fit together? Now in paperback and fortified with exercises, this book delivers a concentrated course in modern statistical thinking. Beginning with classical inferential theories - Bayesian, frequentist, Fisherian - individual chapters take up a series of influential topics: survival analysis, logistic regression, empirical Bayes, the jackknife and bootstrap, random forests, neural networks, Markov Chain Monte Carlo, inference after model selection, and dozens more. The distinctly modern approach integrates methodology and algorithms with statistical inference. Each chapter ends with class-tested exercises, and the book concludes with speculation on the future direction of statistics and data science.Table of ContentsPart I. Classic Statistical Inference: 1. Algorithms and inference; 2. Frequentist inference; 3. Bayesian inference; 4. Fisherian inference and maximum likelihood estimation; 5. Parametric models and exponential families; Part II. Early Computer-Age Methods: 6. Empirical Bayes; 7. James–Stein estimation and ridge regression; 8. Generalized linear models and regression trees; 9. Survival analysis and the EM algorithm; 10. The jackknife and the bootstrap; 11. Bootstrap confidence intervals; 12. Cross-validation and Cp estimates of prediction error; 13. Objective Bayes inference and Markov chain Monte Carlo; 14. Statistical inference and methodology in the postwar era; Part III. Twenty-First-Century Topics: 15. Large-scale hypothesis testing and false-discovery rates; 16. Sparse modeling and the lasso; 17. Random forests and boosting; 18. Neural networks and deep learning; 19. Support-vector machines and kernel methods; 20. Inference after model selection; 21. Empirical Bayes estimation strategies; Epilogue; References; Author Index; Subject Index.

Read more less

Book SynopsisINTERNET OF HEALTHCARE THINGS The book addresses privacy and security issues providing solutions through authentication and authorization mechanisms, blockchain, fog computing, machine learning algorithms, so that machine learning-enabled IoT devices can deliver information concealed in data for fast, computerized responses and enhanced decision-making. The main objective of this book is to motivate healthcare providers to use telemedicine facilities for monitoring patients in urban and rural areas and gather clinical data for further research. To this end, it provides an overview of the Internet of Healthcare Things (IoHT) and discusses one of the major threats posed by it, which is the data security and data privacy of health records. Another major threat is the combination of numerous devices and protocols, precision time, data overloading, etc. In the IoHT, multiple devices are connected and communicate through certain protocols. Therefore, the application of emTable of ContentsPreface xiii Section 1: Security and Privacy Concern in IoHT 1 1 Data Security and Privacy Concern in the Healthcare System 3Ahuja Sourav 1.1 Introduction 3 1.2 Privacy and Security Concerns on E-Health Data 6 1.3 Levels of Threat to Information in Healthcare Organizations 6 1.4 Security and Privacy Requirement 9 1.5 Security of Healthcare Data 11 1.5.1 Existing Solutions 11 1.5.2 Future Challenges in Security and Privacy in the Healthcare Sector 15 1.5.3 Future Work to be Done in Security and Privacy in the Healthcare Sector 16 1.6 Privacy-Preserving Methods in Data 18 1.7 Conclusion 22 References 23 2 Authentication and Authorization Mechanisms for Internet of Healthcare Things 27Srinivasan Lakshmi Narasimhan 2.1 Introduction 28 2.2 Stakeholders in IoHT 29 2.3 IoHT Process Flow 31 2.4 Sources of Vulnerability 33 2.5 Security Features 34 2.6 Challenges to the Security Fabric 35 2.7 Security Techniques—User Authentication 36 2.8 Conclusions 37 References 38 3 Security and Privacy Issues Related to Big Data-Based Ubiquitous Healthcare Systems 41Jaspreet Singh 3.1 Introduction 41 3.2 Big Data Privacy & Security Issues 42 3.3 Big Data Security Problem 43 3.3.1 Big Data Security Lifecycle 44 3.3.2 Threats & Attacks on Big Data 47 3.3.3 Current Technologies in Use 48 3.4 Privacy of Big Data in Healthcare 50 3.4.1 Data Protection Acts 50 3.4.1.1 HIPAA Compliance 50 3.4.1.2 HIPAA Five Rules 53 3.5 Privacy Conserving Methods in Big Data 56 3.6 Conclusion 60 References 61 Section 2: Application of Machine Learning, Blockchain and Fog Computing on IoHT 65 4 Machine Learning Aspects for Trustworthy Internet of Healthcare Things 67Pradeep Bedi, S.B. Goyal, Jugnesh Kumar and Preetishree Patnaik 4.1 Introduction 68 4.2 Overview of Internet of Things 69 4.2.1 Application Area of IoT 72 4.2.1.1 Wearable Devices 73 4.2.1.2 Smart Home Applications 73 4.2.1.3 Healthcare IoT Applications 73 4.2.1.4 Smart Cities 73 4.2.1.5 Smart Agriculture 74 4.2.1.6 Industrial Internet of Things 74 4.3 Security Issues of IoT 74 4.3.1 Authentication 75 4.3.2 Integrity 75 4.3.3 Confidentiality 75 4.3.4 Non-Repudiation 75 4.3.5 Authorization 76 4.3.6 Availability 76 4.3.7 Forward Secrecy 76 4.3.8 Backward Secrecy 76 4.4 Internet of Healthcare Things (IoHT): Architecture and Challenges 76 4.4.1 IoHT Support 77 4.4.2 IoHT Architecture and Data Processing Stages 78 4.4.3 Benefits Associated With Healthcare Based on the IoT 80 4.4.4 Challenges Faced by IoHT 81 4.4.5 Needs in IoHT 81 4.5 Security Protocols in IoHT 82 4.5.1 Key Management 83 4.5.2 User/Device Authentication 83 4.5.3 Access Control/User Access Control 83 4.5.4 Intrusion Detection 83 4.6 Application of Machine Learning for Intrusion Detection in IoHT 84 4.7 Proposed Framework 86 4.8 Conclusion 90 References 90 5 Analyzing Recent Trends and Public Sentiment for Internet of Healthcare Things and Its Impact on Future Health Crisis 95Upendra Dwivedi 5.1 Introduction 96 5.2 Literature Review 97 5.3 Overview of the Internet of Healthcare Things 100 5.4 Performing Topic Modeling on IoHTs Dataset 104 5.5 Performing Sentiment Analysis on IoHTs Dataset 107 5.6 Conclusion and Future Scope 110 References 111 6 Rise of Telemedicine in Healthcare Systems Using Machine Learning: A Key Discussion 113Shaweta Sachdeva and Aleem Ali 6.1 Introduction 114 6.2 Types of Machine Learning 115 6.3 Telemedicine Advantages 115 6.4 Telemedicine Disadvantages 116 6.5 Review of Literature 116 6.6 Fundamental Key Components Needed to Begin Telemedicine 118 6.6.1 Collaboration Instruments 118 6.6.2 Clinical Peripherals 119 6.6.3 Work Process 119 6.6.4 Cloud-Based Administrations 119 6.7 Types of Telemedicine 119 6.7.1 Store-and-Forward Method 119 6.7.1.1 Telecardiology 120 6.7.1.2 Teleradiology 121 6.7.1.3 Telepsychiatry 121 6.7.1.4 Telepharmacy 121 6.7.2 Remote Monitoring 123 6.7.3 Interactive Services 123 6.8 Benefits of Telemedicine 124 6.9 Application of Telemedicine Using Machine Learning 125 6.10 Innovation Infrastructure of Telemedicine 125 6.11 Utilization of Mobile Wireless Devices in Telemedicine 126 6.12 Conclusion 127 References 128 7 Trusted Communication in the Healthcare Sector Using Blockchain 131Balasamy K. 7.1 Introduction 131 7.2 Overview of Blockchain 133 7.3 Medical IoT Concerns 134 7.3.1 Security Concerns 134 7.3.2 Privacy Concerns 135 7.3.3 Trust Concerns 135 7.4 Needs for Security in Medical IoT 135 7.5 Uses of Blockchain in Healthcare 137 7.6 Solutions for IoT Healthcare Cyber-Security 138 7.6.1 Architecture of the Smart Healthcare System 139 7.6.1.1 Data Perception Layer 139 7.6.1.2 Data Communication Layer 140 7.6.1.3 Data Storage Layer 140 7.6.1.4 Data Application Layer 140 7.7 Executions of Trusted Environment 140 7.7.1 Root of Trust Security Services 141 7.7.2 Chain of Trust Security Services 143 7.8 Patient Registration Using Medical IoT Devices 144 7.8.1 Encryption 145 7.8.2 Key Generation 146 7.8.3 Security by Isolation 146 7.8.4 Virtualization 146 7.9 Trusted Communications Using Blockchain 149 7.9.1 Record Creation Using IoT Gateways 150 7.9.2 Accessibility to Patient Medical History 151 7.9.3 Patient Enquiry With the Hospital Authority 151 7.9.4 Blockchain-Based IoT System Architecture 151 7.9.4.1 First Layer 151 7.9.4.2 Second Layer 152 7.9.4.3 Third Layer 152 7.10 Combined Workflows 152 7.10.1 Layer 1: The Gateway Collects IoT Data and Generates a New Record 152 7.10.2 Layer 2: Gateway/Authority Want to Access Patient’s Medical Record 153 7.10.3 Layer 3: Patient Visits and Interact With an Authority 153 7.11 Conclusions 154 References 154 8 Blockchain in Smart Healthcare Management 161Jayant Barak, Harshwardhan Chaudhary, Rakshit Mangal, Aarti Goel and Deepak Kumar Sharma 8.1 Introduction 162 8.2 Healthcare Industry 163 8.2.1 Classification of Healthcare Services 163 8.2.2 Health Information Technology (HIT) 164 8.2.3 Issues and Challenges Faced by Major Stakeholders in the Healthcare Industry 165 8.2.3.1 The Patient 166 8.2.3.2 The Pharmaceutical Industry 166 8.2.3.3 The Healthcare Service Providers 166 8.2.3.4 The Government 167 8.2.3.5 Insurance Company 167 8.3 Blockchain Technology 168 8.3.1 Important Terms 168 8.3.2 Features of Blockchain 170 8.3.2.1 Decentralization 170 8.3.2.2 Immutability 170 8.3.2.3 Transparency 171 8.3.2.4 Smart Contracts 171 8.3.3 Workings of a Blockchain System 171 8.3.4 Applications of Blockchain 173 8.3.4.1 Financial Services 173 8.3.4.2 Healthcare 173 8.3.4.3 Supply Chain 173 8.3.4.4 Identity Management 173 8.3.4.5 Voting 173 8.3.5 Challenges and Drawbacks of Blockchain 174 8.4 Applications of Blockchain in Healthcare 176 8.4.1 Electronic Medical Records (EMR) and Electronic Health Records (EHR) 176 8.4.2 Management System 177 8.4.3 Remote Monitoring/IoMT 178 8.4.4 Insurance Industry 179 8.4.5 Drug Counterfeiting 180 8.4.6 Clinical Trials 182 8.4.7 Public Health Management 182 8.5 Challenges of Blockchain in Healthcare 183 8.6 Future Research Directions 184 8.7 Conclusion 185 References 186 Section 3: Case Studies of Healthcare 189 9 Organ Trafficking on the Dark Web—The Data Security and Privacy Concern in Healthcare Systems 191Romil Rawat, Bhagwati Garg, Vinod Mahor, Shrikant Telang, Kiran Pachlasiya and Mukesh Chouhan 9.1 Introduction 192 9.2 Inclination for Cybersecurity Web Peril 194 9.3 Literature Review 197 9.4 Market Paucity or Organ Donors 199 9.5 Organ Harvesting and Transplant Tourism Revenue 203 9.6 Social Web Net Crimes 204 9.7 DW—Frontier of Illicit Human Harvesting 209 9.8 Organ Harvesting Apprehension 209 9.9 Result and Discussions 212 9.10 Conclusions 212 References 213 10 Deep Learning Techniques for Data Analysis Prediction in the Prevention of Heart Attacks 217C.V. Aravinda, Meng Lin, Udaya Kumar, Reddy K.R. and G. Amar Prabhu Abbreviations 218 10.1 Introduction 218 10.2 Literature Survey 219 10.3 Materials and Method 221 10.3.1 Cohort Study 222 10.4 Training Models 222 10.4.1 Artificial Neural Network (ANN) 222 10.4.2 K-Nearest Neighbor Classifier 224 10.4.3 Naïve Bayes Classifier 225 10.4.4 Decision Tree Classifier (DTC) 226 10.4.5 Random Forest Classifier (RFC) 226 10.4.6 Neural Network Implementation 226 10.5 Data Preparation 227 10.5.1 Multi-Layer Perceptron Neural Network (MLPNN) Algorithm and Prediction 227 10.6 Results Obtained 228 10.6.1 Accuracy 228 10.6.2 Data Analysis 228 10.7 Conclusion 236 References 236 11 Supervising Healthcare Schemes Using Machine Learning in Breast Cancer and Internet of Things (SHSMLIoT) 241Monika Lamba, Geetika Munjal and Yogita Gigras 11.1 Introduction 242 11.2 Related Work 245 11.3 IoT and Disease 250 11.4 Research Materials and Methods 251 11.4.1 Dataset 251 11.4.2 Data Pre-Processing 252 11.4.3 Classification Algorithms 252 11.5 Experimental Outcomes 253 11.6 Conclusion 257 References 258 12 Perspective-Based Studies of Trust in IoHT and Machine Learning-Brain Cancer 265Sweta Kumari, Akhilesh Kumar Sharma, Sandeep Chaurasia and Shamik Tiwari 12.1 Introduction 266 12.2 Literature Survey 267 12.3 Illustration of Brain Cancer 268 12.3.1 Brain Tumor 268 12.3.2 Types of Brain Tumors 269 12.3.3 Grades of Brain Tumors 270 12.3.4 Symptoms of Brain Tumors 271 12.4 Sleuthing and Classification of Brain Tumors 273 12.4.1 Sleuthing of Brain Tumors 273 12.4.2 Challenges During Classification of Brain Tumors 274 12.5 Survival Rate of Brain Tumors 274 12.6 Conclusion 278 References 279 Index 281

Read more less

Book SynopsisIn recent years the development of new classification and regression algorithms based on deep learning has led to a revolution in the fields of artificial intelligence, machine learning, and data analysis. The development of a theoretical foundation to guarantee the success of these algorithms constitutes one of the most active and exciting research topics in applied mathematics. This book presents the current mathematical understanding of deep learning methods from the point of view of the leading experts in the field. It serves both as a starting point for researchers and graduate students in computer science, mathematics, and statistics trying to get into the field and as an invaluable reference for future research.Table of Contents1. The modern mathematics of deep learning Julius Berner, Philipp Grohs, Gitta Kutyniok and Philipp Petersen; 2. Generalization in deep learning Kenji Kawaguchi, Leslie Pack Kaelbling, and Yoshua Bengio; 3. Expressivity of deep neural networks Ingo Gühring, Mones Raslan and Gitta Kutyniok; 4. Optimization landscape of neural networks René Vidal, Zhihui Zhu and Benjamin D. Haeffele; 5. Explaining the decisions of convolutional and recurrent neural networks Wojciech Samek, Leila Arras, Ahmed Osman, Grégoire Montavon and Klaus-Robert Müller; 6. Stochastic feedforward neural networks: universal approximation Thomas Merkh and Guido Montúfar; 7. Deep learning as sparsity enforcing algorithms A. Aberdam and J. Sulam; 8. The scattering transform Joan Bruna; 9. Deep generative models and inverse problems Alexandros G. Dimakis; 10. A dynamical systems and optimal control approach to deep learning Weinan E, Jiequn Han and Qianxiao Li; 11. Bridging many-body quantum physics and deep learning via tensor networks Yoav Levine, Or Sharir, Nadav Cohen and Amnon Shashua.

Read more less

Book SynopsisData assimilation is a hugely important mathematical technique, relevant in fields as diverse as geophysics, data science, and neuroscience. This modern book provides an authoritative treatment of the field as it relates to several scientific disciplines, with a particular emphasis on recent developments from machine learning and its role in the optimisation of data assimilation. Underlying theory from statistical physics, such as path integrals and Monte Carlo methods, are developed in the text as a basis for data assimilation, and the author then explores examples from current multidisciplinary research such as the modelling of shallow water systems, ocean dynamics, and neuronal dynamics in the avian brain. The theory of data assimilation and machine learning is introduced in an accessible and unified manner, and the book is suitable for undergraduate and graduate students from science and engineering without specialized experience of statistical physics.Table of Contents1. Prologue: linking 'The Future' with the present; 2. A data assimilation reminder; 3. Remembrance of things path; 4. SDA variational principles; Euler–Lagrange equations and Hamiltonian formulation; 5. Using waveform information; 6. Annealing in the model precision Rf; 7. Discrete time integration in data assimilation variational principles; Lagrangian and Hamiltonian formulations; 8. Monte Carlo methods; 9. Machine learning and its equivalence to statistical data assimilation; 10. Two examples of the practical use of data assimilation; 11. Unfinished business; Bibliography; Index.

Read more less

Book SynopsisWhat is an artificial intelligence (AI)-enabled drone and what can it do? Are AI-enabled drones better than human-controlled drones? This book will answer these questions and more, and empower you to develop your own AI-enabled drone.You''ll progress from a list of specifications and requirements, in small and iterative steps, which will then lead to the development of Unified Modeling Language (UML) diagrams based in part to the standards established by for the Robotic Operating System (ROS). The ROS architecture has been used to develop land-based drones. This will serve as a reference model for the software architecture of unmanned systems. Using this approach you''ll be able to develop a fully autonomous drone that incorporates object-oriented design and cognitive deep learning systems that adapts to multiple simulation environments. These multiple simulation environments will also allow you to further build public trustTable of ContentsIntelligent Autonomous Drones with Cognitive Deep LearningChapter 1. Defining the Required Goals, Specifications, and RequirementsChapter 2. UML Systems for Reliable and Robust AI enabled Self-Driving DronesChapter 3. Setting Your Main Virtual Linux SystemChapter 4. Understanding Advanced Anaconda ConceptsChapter 5. Understanding Drone-Kit for Testing and Programming your Self-Driving DroneChapter 6. Understanding, Maintaining, and Controlling the DRIVING Trajectory of the AI Rover DroneChapter 7. AI Enabled Rover Drone Vision with the Python OpenCV LibraryChapter 8. Your First Experience with Creating Drone Reinforcement Learning for Self-Driving and ExploringChapter 9. AI Enabled Rover Drones with Advanced Deep LearningChapter 10. Nature's other Secrets (Uncertainty, Bayesian Deep Learning, and Evolutionary Computing for Rovers)Chapter 11. Building the Ultimate Cognitive Deep Learning Land-Rover ControllerChapter 12. AI Drone Verification and Validation with Computer SimulationsChapter 13. The Critical Need for Geo-Spatial Guidance for AI Rover DronesChapter 14. Statistics and Experimental Algorithms for Drone EnhancementsChapter 15. The Robotic Operating System (ROS) Architecture for AI enabled Land-Based Rover Drones.Chapter 16. Putting it all together and the Testing Required.Chapter 17. “It’s Alive! It’s Alive!” (Facing Ones Very Own Creation)Chapter 18. Your Creation can be your Best Friend or your Worst Nightmare.

Read more less

Book SynopsisGo beyond the basics and build complete applications using the Rust programming language, updated for Rust 2021 edition. The applications you''ll build over the course of this book include a high-performance web client, an embedded computer (for a robot, for example), a game, a serverless web app, and an application that incorporates AI and machine learning.   Each chapter is organized in the following format: what the kind of should application look like; requirements and user stories of our example program; an introduction to the Rust libraries used; the actual implementation of the example program, including common pitfalls and their solutions; and a brief comparison of libraries for building each application, if there is no clear preference. Practical Rust Projects, Second Edition will open your eyes to how Rust can be put to practical, real-world use. After reading this book, you will be able to use Rust to build a varTable of Contents1. Welcome to the World of Rust2. Building a Command-Line Program3. Creating Graphical User Interfaces (GUIs)4. High-performance Web Frontend using WebAssembly5. Building REST APIs6. Going Serverless with Amazon AWS Rust SDK7. Building a Game8. Physical Computing in Rust9. Artificial Intelligence and Machine Learning10. What else can you do with Rust?---------------------------------------------------------1. Welcome to the World of Rust * Add a note on what's changed in the 2nd edition. * Add a note on Rust 20212. Building a Command-Line Program3. Creating Graphical User Interfaces (GUIs) * Upgrade to GTK 4?4. High-performance Web Frontend using WebAssembly5. Building REST APIs 6. 6. Going Serverless with Amazon AWS Rust SDK * Using the new AWS SDK for Rust and Rust runtime for AWS Lambda7. Building a Game * Use a different game engine because the one used in the 1st edition seized development8. Physical Computing in Rust * Maybe add a section on using WebAssembly on RPi9. Artificial Intelligence and Machine Learning * Maybe add a section on deep learning10. What else can you do with Rust? * Remove the web part that is included in 2nd edition

Read more less

Book SynopsisMigrate from pandas and scikit-learn to PySpark to handle vast amounts of data and achieve faster data processing time. This book will show you how to make this transition by adapting your skills and leveraging the similarities in syntax, functionality, and interoperability between these tools. Distributed Machine Learning with PySpark offers a roadmap to data scientists considering transitioning from small data libraries (pandas/scikit-learn) to big data processing and machine learning with PySpark. You will learn to translate Python code from pandas/scikit-learn to PySpark to preprocess large volumes of data and build, train, test, and evaluate popular machine learning algorithms such as linear and logistic regression, decision trees, random forests, support vector machines, Naïve Bayes, and neural networks. After completing this book, you will understand the foundational concepts of data preparation and machine learning and will have the skills necessary toapply these methods using PySpark, the industry standard for building scalable ML data pipelines. What You Will LearnMaster the fundamentals of supervised learning, unsupervised learning, NLP, and recommender systemsUnderstand the differences between PySpark, scikit-learn, and pandasPerform linear regression, logistic regression, and decision tree regression with pandas, scikit-learn, and PySparkDistinguish between the pipelines of PySpark and scikit-learnWho This Book Is ForData scientists, data engineers, and machine learning practitioners who have some familiarity with Python, but who are new to distributed machine learning and the PySpark framework.Table of ContentsChapter 1: An Easy Transition.- Chapter 2: Selecting Algorithms.- Chapter 3: Multiple Linear Regression with Pandas, Scikit-Learn, and PySpark.- Chapter 4: Decision Trees for Regression with Pandas, Scikit-Learn, and PySpark.- Chapter 5: Random Forests for Regression with Pandas, Scikit-Learn, and PySpark.- Chapter 6: Gradient-Boosted Tree Regression with Pandas, Scikit-Learn and PySpark.- Chapter 7: Logistic Regression with Pandas, Scikit-Learn and PySpark.-  Chapter 8: Decision Tree Classification with Pandas, Scikit-Learn and PySpark.- Chapter 9: Random Forest Classification with Scikit-Learn and PySpark.- Chapter 10: Support Vector Machine Classification with Pandas, Scikit-Learn and PySpark.- Chapter 11: Naïve Bayes Classification with Pandas, Scikit-Learn and PySpark.- Chapter 12: Neural Network Classification with Pandas, Scikit-Learn and PySpark.- Chapter 13: Recommender Systems with Pandas, Surprise and PySpark.- Chapter 14: Natural Language Processing with Pandas, Scikit-Learn and PySpark.- Chapter 15: K-Means Clustering with Pandas, Scikit-Learn and PySpark.- Chapter 16: Hyperparameter Tuning with Scikit-Learn and PySpark.- Chapter 17: Pipelines with Scikit-Learn and PySpark.- Chapter 18: Deploying Models in Production with Scikit-Learn and PySpark.  

Read more less

Book SynopsisWhile many introductory guides to AI are calculus books in disguise, this one mostly eschews the math. Instead, author Jeff Prosise helps engineers and software developers build an intuitive understanding of AI to solve business problems.

Read more less

Book SynopsisArtificial Intelligence is the most exciting technology of the century, and Deep Learning is, quite literally, the “brain” behind the world’s smartest Artificial Intelligence systems out there. Grokking Deep Learning is the perfect place to begin the deep learning journey. Rather than just learning the “black box” API of some library or framework, readers will actually understand how to build these algorithms completely from scratch. Key Features:Build neural networks that can see and understand images Build an A.I. that will learn to defeat you in a classic Atari gameHands-on Learning Written for readers with high school-level math and intermediateprogramming skills. Experience with Calculus is helpful but notrequired. ABOUT THE TECHNOLOGY Deep Learning is a subset of Machine Learning, which is a field dedicated to the study and development of machines that can learn, often with the goal of eventually attaining general artificial intelligence.

Read more less

Book SynopsisAt its core, machine learning is about efficiently identifying patterns and relationships in data. Many tasks, such as finding associations among terms so you can make accurate search recommendations or locating individuals within a social network who have similar interests, are naturally expressed as graphs. Graph-Powered Machine Learning introduces you to graph technology concepts, highlighting the role of graphs in machine learning and big data platforms. You’ll get an in-depth look at techniques including data source modeling, algorithm design, link analysis, classification, and clustering. As you master the core concepts, you’ll explore three end-to-end projects that illustrate architectures, best design practices, optimization approaches, and common pitfalls. Key Features · The lifecycle of a machine learning project · Three end-to-end applications · Graphs in big data platforms · Data source modeling · Natural language processing, recommendations, and relevant search · Optimization methods Readers comfortable with machine learning basics. About the technology By organizing and analyzing your data as graphs, your applications work more fluidly with graph-centric algorithms like nearest neighbor or page rank where it’s important to quickly identify and exploit relevant relationships. Modern graph data stores, like Neo4j or Amazon Neptune, are readily available tools that support graph-powered machine learning. Alessandro Negro is a Chief Scientist at GraphAware. With extensive experience in software development, software architecture, and data management, he has been a speaker at many conferences, such as Java One, Oracle Open World, and Graph Connect. He holds a Ph.D. in Computer Science and has authored several publications on graph-based machine learning.

Read more less

Book SynopsisThe Spark distributed data processing platform provides an easy-to-implement tool for ingesting, streaming, and processing data from any source. In Spark in Action, Second Edition, you’ll learn to take advantage of Spark’s core features and incredible processing speed, with applications including real-time computation, delayed evaluation, and machine learning. Unlike many Spark books written for data scientists, Spark in Action, Second Edition is designed for data engineers and software engineers who want to master data processing using Spark without having to learn a complex new ecosystem of languages and tools. You’ll instead learn to apply your existing Java and SQL skills to take on practical, real-world challenges. Key Features · Lots of examples based in the Spark Java APIs using real-life dataset and scenarios · Examples based on Spark v2.3 Ingestion through files, databases, and streaming · Building custom ingestion process · Querying distributed datasets with Spark SQL For beginning to intermediate developers and data engineers comfortable programming in Java. No experience with functional programming, Scala, Spark, Hadoop, or big data is required. About the technology Spark is a powerful general-purpose analytics engine that can handle massive amounts of data distributed across clusters with thousands of servers. Optimized to run in memory, this impressive framework can process data up to 100x faster than most Hadoop-based systems. Author BioAn experienced consultant and entrepreneur passionate about all things data, Jean-Georges Perrin was the first IBM Champion in France, an honor he’s now held for ten consecutive years. Jean-Georges has managed many teams of software and data engineers.

Read more less

Book SynopsisThe mathematical paradigms that underlie deep learning typically start out as hard-to-read academic papers, often leaving engineers in the dark about how their models actually function. Math and Architectures of Deep Learning bridges the gap between theory and practice, laying out the math of deep learning side by side with practical implementations in Python and PyTorch. Written by deep learning expert Krishnendu Chaudhury, you'll peer inside the “black box” to understand how your code is working, and learn to comprehend cutting-edge research you can turn into practical applications. about the technology It's important to understand how your deep learning models work, both so that you can maintain them efficiently and explain them to other stakeholders. Learning mathematical foundations and neural network architecture can be challenging, but the payoff is big. You'll be free from blind reliance on pre-packaged DL models and able to build, customize, and re-architect for your specific needs. And when things go wrong, you'll be glad you can quickly identify and fix problems. about the book Math and Architectures of Deep Learning sets out the foundations of DL in a way that's both useful and accessible to working practitioners. Each chapter explores a new fundamental DL concept or architectural pattern, explaining the underpinning mathematics and demonstrating how they work in practice with well-annotated Python code. You'll start with a primer of basic algebra, calculus, and statistics, working your way up to state-of-the-art DL paradigms taken from the latest research. By the time you're done, you'll have a combined theoretical insight and practical skills to identify and implement DL architecture for almost any real-world challenge. Trade Review'This is a book that will reward your patience and perseverance with a clear and detailed knowledge of deep learning mathematics and associated techniques.' Tony Holdroyd 'Most online machine learning courses teach you how to get stuff done, but they don't give you the underlying math. If you want to know, this is the book for you!' Wiebe de Jong 'A really interesting book for people that want to understand the underlying mathematical mechanism of deep learning.' Julien Pohie 'Gives a unique perspective about machine learning and mathematical approaches.' Krzysztof Kamyczek 'An awesome book to get the grasp of the important mathematical skills to understand the very basics of deep learning.' Nicole KoenigsteinTable of Contentstable of contents READ IN LIVEBOOK 1AN OVERVIEW OF MACHINE LEARNING AND DEEP LEARNING READ IN LIVEBOOK 2INTRODUCTION TO VECTORS, MATRICES AND TENSORS FROM MACHINE LEARNING AND DATA SCIENCE POINT OF VIEW READ IN LIVEBOOK 3INTRODUCTION TO VECTOR CALCULUS FROM MACHINE LEARNING POINT OF VIEW READ IN LIVEBOOK 4LINEAR ALGEBRAIC TOOLS IN MACHINE LEARNING AND DATA SCIENCE READ IN LIVEBOOK 5PROBABILITY DISTRIBUTIONS FOR MACHINE LEARNING AND DATA SCIENCE READ IN LIVEBOOK 6BAYESIAN TOOLS FOR MACHINE LEARNING AND DATA SCIENCE READ IN LIVEBOOK 7FUNCTION APPROXIMATION: HOW NEURAL NETWORKS MODEL THE WORLD READ IN LIVEBOOK 8TRAINING NEURAL NETWORKS: FORWARD AND BACKPROPAGATION READ IN LIVEBOOK 9LOSS, OPTIMIZATION AND REGULARIZATION READ IN LIVEBOOK 10ONE, TWO AND THREE DIMENSIONAL CONVOLUTION AND TRANSPOSED CONVOLUTION IN NEURAL NETWORKS 11 IMAGE ANALYSIS: 2D CONVOLUTION BASED NEURAL NETWORK ARCHITECTURES FOR OBJECT RECOGNITION AND DETECTION 12 VIDEO ANALYSIS: 3D CONVOLUTION BASED SPATIO TEMPORAL NEURAL NETWORK ARCHITECTURES READ IN LIVEBOOK APPENDIX A: APPENDIX A.1Dot Product and cosine of the angle between two vectors A.2Computing variance of Gaussian Distribution A.3Two Theorems in Statistic

Read more less

Book Synopsis"The first edition of Deep Learning with Python is one of the best books on the subject. The second edition made it even better." - Todd Cook The bestseller revised! Deep Learning with Python, Second Edition is a comprehensive introduction to the field of deep learning using Python and the powerful Keras library. Written by Google AI researcher François Chollet, the creator of Keras, this revised edition has been updated with new chapters, new tools, and cutting-edge techniques drawn from the latest research. You'll build your understanding through practical examples and intuitive explanations that make the complexities of deep learning accessible and understandable. about the technologyMachine learning has made remarkable progress in recent years. We've gone from near-unusable speech recognition, to near-human accuracy. From machines that couldn't beat a serious Go player, to defeating a world champion. Medical imaging diagnostics, weather forecasting, and natural language question answering have suddenly become tractable problems. Behind this progress is deep learning—a combination of engineering advances, best practices, and theory that enables a wealth of previously impossible smart applications across every industry sector about the bookDeep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. You'll learn directly from the creator of Keras, François Chollet, building your understanding through intuitive explanations and practical examples. Updated from the original bestseller with over 50% new content, this second edition includes new chapters, cutting-edge innovations, and coverage of the very latest deep learning tools. You'll explore challenging concepts and practice with applications in computer vision, natural-language processing, and generative models. By the time you finish, you'll have the knowledge and hands-on skills to apply deep learning in your own projects. what's insideDeep learning from first principlesImage-classification, imagine segmentation, and object detectionDeep learning for natural language processingTimeseries forecastingNeural style transfer, text generation, and image generation about the readerReaders need intermediate Python skills. No previous experience with Keras, TensorFlow, or machine learning is required. about the authorFrançois Chollet works on deep learning at Google in Mountain View, CA. He is the creator of the Keras deep-learning library, as well as a contributor to the TensorFlow machine-learning framework. He also does AI research, with a focus on abstraction and reasoning. His papers have been published at major conferences in the field, including the Conference on Computer Vision and Pattern Recognition (CVPR), the Conference and Workshop on Neural Information Processing Systems (NIPS), the International Conference on Learning Representations (ICLR), and others.Trade Review"The first edition of Deep Learning with Python is one of the best books on the subject. The second edition made it even better. " Todd Cook "Really easy to read and gives practical examples and easy to understand explanations of the concepts behind deep learning." Billy O'Callaghan "A tell-tale book that tells you all the secrets of deep learning!" Nikos Kanakaris "A great refresher of the old concepts explored in new and exciting ways. Manifold hypothesis steals the show!" Sayak Paul "One of the best books on this topic." Rauhsan Jha "The book is full of insights, useful both for the novice and the more experienced machine learning professional." Viton Vitanis "This is the book to read if you want to learn DL." Kjell Jansson "Francois explains everything in a very lucid & systematic manner, this approach of writing certainly gives confidence in users." Rauhsan Jha

Read more less

Book SynopsisOptimise the performance of your systems with practical experiments used by engineers in the world's most competitive industries. Experimentation for Engineers: From A/B testing to Bayesian optimization is a toolbox of techniques for evaluating new features and fine-tuning parameters. You will start with a deep dive into methods like A/B testing and then graduate to advanced techniques used to measure performance in industries such as finance and social media. You will learn how to: Design, run, and analyse an A/B test Break the "feedback loops" caused by periodic retraining of ML models Increase experimentation rate with multi-armed bandits Tune multiple parameters experimentally with Bayesian optimisation Clearly define business metrics used for decision-making Identify and avoid the common pitfalls of experimentation By the time you're done, you will be able to seamlessly deploy experiments in production, whilst avoiding common pitfalls. About the technology Does my software really work? Did my changes make things better or worse? Should I trade features for performance? Experimentation is the only way to answer questions like these. This unique book reveals sophisticated experimentation practices developed and proven in the world's most competitive industries and will help you enhance machine learning systems, software applications, and quantitative trading solutions.Trade Review"Putting an 'improved' version of a system into production can be really risky. This book focuses you on what is important!" Simone Sguazza, University of Applied Sciences and Arts of Southern Switzerland "A must-have for anyone setting up experiments, from A/B tests to contextual bandits and Bayesian optimization." Maxim Volgin, KLM "Shows a non-mathematical programmer exactly what they need to write powerful mathematically-based testing algorithms." Patrick Goetz, The University of Texas at Austin "Gives you the tools you need to get the most out of your experiments." Marc-Anthony Taylor, Raiffeisen Bank International

Read more less

Book SynopsisMachine Learning Engineering in Action lays out an approach to building deployable, maintainable production machine learning systems. You will adopt software development standards that deliver better code management, and make it easier to test, scale, and even reuse your machine learning code! You will learn how to plan and scope your project, manage cross-team logistics that avoid fatal communication failures, and design your code's architecture for improved resilience. You will even discover when not to use machine learning—and the alternative approaches that might be cheaper and more effective. When you're done working through this toolbox guide, you will be able to reliably deliver cost-effective solutions for organizations big and small alike. Following established processes and methodology maximizes the likelihood that your machine learning projects will survive and succeed for the long haul. By adopting standard, reproducible practices, your projects will be maintainable over time and easy for new team members to understand and adapt. Trade Review“Anice view on practical data science and machine learning. Great reading fornewbies, some interesting views for seasoned practitioners.” Johannes Verwijnen “Amust read for those looking to balance the planning and experimentationlifecycle.” Jesús Antonino Juárez Guerrero “Apractical book to help engineers understand the workflow of machine learningprojects.” Xiangbo Mao “Donot implement your ML model into production without reading this book!” Lokesh Kumar

Read more less

Book SynopsisFascinating' Greta ThunbergExtraordinary' Merlin SheldrakeA must-read' New ScientistEnthralling' George MonbiotBrilliant' Philip HoareAs a biologist and nature filmmaker, Tom Mustill had always liked whales. But when one landed on his kayak, nearly killing him, the video clip of the event going viral, he became obsessed.This book traces an extraordinary investigation into the deep ocean and today's cutting-edge science. Using underwater ears,' robotic fish, big data and machine intelligence, leading scientists and tech-entrepreneurs across the world are working to turn the fantasy of Dr Dolittle into a reality, upending much of what we know about these mysterious creatures. But what would it mean if we were to make contact? Can we hope to one day understand animals? Are we ready for what they might say?Enormously original and hugely entertaining, How to Speak Whale is an unforgettable look at how close we truly are to communicating with another species and how doing so might change our world beyond recognition.Trade Review‘A rich exploration of some of the world's most astonishing creatures … Mustill weaves a narrative that will expand your concept of language and deepen your understanding of the many ways there are to be alive. This is an extraordinary book that left me inspired’ Merlin Sheldrake, author of Entangled Life ‘A must-read… a hugely engaging personal story of a journey into the future of human-animal communication facilitated by delving into its past’ New Scientist ‘[An] extensively researched and energetic book… it is via the informed, far-reaching empathy of intermediaries such as Mustill that we stand our best chance of seeing into the non-human depths’ New Statesman ‘First-class … Reasoned, entertaining, and fact-filled’ Forbes ‘Fascinating and deeply humane’ Greta Thunberg ‘A rich, enthralling, brilliant book that opens our eyes and ears to worlds we can scarcely imagine’George Monbiot, Sunday Times bestselling author of Regenesis ‘Tantalizing … Think how transformative it would be if we could chat with whales about their love lives or their sorrows or their thoughts on the philosophy of language’ Elizabeth Kolbert, New Yorker ‘Mind-blowing … You will never feel closer to the magnificence of whales’Lucy Jones, author of Losing Eden ‘A scary, important and brilliant book … If we do get to translate ‘whale’, will we like what they’ve got to say?’Philip Hoare, author of Leviathan ‘Mustill takes us farther, much farther, than Dr. Dolittle ever imagined’ Carl Safina ‘Riveting … One of the most exciting and hopeful books I have read in ages’ Sy Montgomery, author of The Soul of an Octopus ‘Mustill conveys the richness of whale song and communication’ Frans de Waal ‘Lively and informative’ Jonathan Slaght, author of Owls of the Eastern Ice ‘Extraordinary’ Christiana Figueres

Read more less

Book SynopsisBridges the gap between AI and neuroscience by telling the story of how the brain came to be.''I found this book amazing'' Daniel Kahneman, Winner of the Nobel Prize in Economics and bestselling author of Thinking Fast & SlowThe entirety of the human brain's 4-billion-year story can be summarised as the culmination of five evolutionary breakthroughs, starting from the very first brains, all the way to the modern human brains. Each breakthrough emerged from new sets of brain modifications, and equipped animals with a new suite of intellectual faculties.These five breakthroughs are the organising map to this book, and they make up our itinerary for our adventure back in time. Each breakthrough also has fascinating corollaries to breakthroughs in AI. Indeed, there will be plenty of such surprises along the way. For instance: the innovation that enabled AI to beat humans in the game of Go temporal difference reinforcement learning was an innovation discovered by our fish ancestors over 500 million years ago. The solutions to many of the current mysteries in AI such as common sense' can be found in the tiny brain of a mouse. Where do emotions come from? Research suggests that they may have arisen simply as a solution to navigation in ancient worm brains. Unravelling this evolutionary story will reveal the hidden features of human intelligence and with them, just how your mind came to be.Trade Review‘Max Bennett published two scientific papers on brain evolution that blew me away. Now he has turned these into a fabulous book, A Brief History of Intelligence. His friendly writing style, clear jargon-free prose, and well of information make this book a winner.’ Joseph LeDoux, Henry and Lucy Moses Professor of Neural Science & Psychology at NYU, bestselling author of Anxious and A Deep History of Ourselves ‘With a truly mindboggling scope, A Brief History of Intelligence integrates the most relevant scientific knowledge to paint the big picture of how the human mind emerged. The red line through this book never gets blurred by unnecessary detail or jargoned language. It makes for exciting reading for virtually everybody, laypersons and experts alike.’ Kurt Kotrschal, Professor at Department of Behavioral Biology at University of Vienna, author of Dog & Human: The secret of our soul mates ‘If you’re in the least bit curious about that 3-pound grey blob between your ears, read this book. Max Bennett’s entertaining and enlightening natural history of brains is a tour de force–as refreshing as it is entertaining. It made my brain happy.’ Jonathan Balcombe, bestselling author of Super Fly, and the New York Times bestseller What a Fish Knows ‘Max Bennett gives a lively account of how brains evolved, and how the brain works today. A Brief History of Intelligence is engaging, comprehensive, and brimming with novel insights.’ Kent Berridge, James Olds Distinguished Professor of Psychology & Neuroscience at University of Michigan ‘If you want to know how our ancestors were able to “weaponize their imaginarium to survive”, then this is the book for you. In fact, this book discloses everything you always wanted to know about the brain (but were afraid to ask). It is an incredible resource.’ Karl Friston, Scientific Director for Wellcome Centre for Human Neuroimaging; Professor at Queen Square Institute of Neurology, University College London

Read more less

Book Synopsis

Read more less

Book Synopsis

Read more less

Book SynopsisA guide to understanding the inner workings and outer limits of technology and why we should never assume that computers always get it right.In Artificial Unintelligence, Meredith Broussard argues that our collective enthusiasm for applying computer technology to every aspect of life has resulted in a tremendous amount of poorly designed systems. We are so eager to do everything digitally—hiring, driving, paying bills, even choosing romantic partners—that we have stopped demanding that our technology actually work. Broussard, a software developer and journalist, reminds us that there are fundamental limits to what we can (and should) do with technology. With this book, she offers a guide to understanding the inner workings and outer limits of technology—and issues a warning that we should never assume that computers always get things right.Making a case against technochauvinism—the belief that technology is always the solution̵

Read more less

Book SynopsisKey concepts, definitions, examples, and historical contexts for understanding smart cities, along with discussions of both drawbacks and benefits of this approach to urban problems.Over the past ten years, urban planners, technology companies, and governments have promoted smart cities with a somewhat utopian vision of urban life made knowable and manageable through data collection and analysis. Emerging smart cities have become both crucibles and showrooms for the practical application of the Internet of Things, cloud computing, and the integration of big data into everyday life. Are smart cities optimized, sustainable, digitally networked solutions to urban problems? Or are they neoliberal, corporate-controlled, undemocratic non-places? This volume in the MIT Press Essential Knowledge series offers a concise introduction to smart cities, presenting key concepts, definitions, examples, and historical contexts, along with discussions of both the drawbacks and the benefits of

Read more less

Book SynopsisTo succeed in data science you need some math proficiency. But not just any math. This common-sense guide provides a clear, plain English survey of the math you'll need in data science, including probability, statistics, hypothesis testing, linear algebra, machine learning, and calculus.

Read more less

Book SynopsisIn this book, you'll learn a holistic approach to designing ML systems that are reliable, scalable, maintainable, and adaptive to changing environments and business requirements.

Read more less

Book SynopsisThe design patterns in this book capture best practices and solutions to recurring problems in machine learning. The authors catalog proven methods to help data scientists tackle common problems throughout the ML process. These design patterns codify the experience of hundreds of experts into straightforward, approachable advice.

Read more less

Book SynopsisThis practical guide from Mike X Cohen teaches the core concepts of linear algebra as implemented in Python, including how they're used in data science, machine learning, deep learning, computational simulations, and biomedical data processing applications

Read more less

Book SynopsisThis practical guide helps your company bring data science to life for different real-world MLOps scenarios. Senior data scientists, MLOps engineers, and machine learning engineers will learn how to tackle challenges that prevent many businesses from moving ML models to production.

Read more less

Book SynopsisThis practical guide provides more than 200 self-contained recipes to help you solve machine learning challenges you may encounter in your work.

Read more less

Book SynopsisIn this book, author Matheus Facure explains the untapped potential of causal inference for estimating impacts and effects.

Read more less

Book SynopsisThis hands-on guide presents three problem-focused ways to learn ML: no code using AutoML, low-code using BigQuery ML, and custom code using scikit-learn and Keras. You'll learn key ML concepts by using real-world datasets with realistic problems.

Read more less

Book SynopsisThe only how-to guide offering a unified, systemic approach to acquiring, cleaning, and managing data in R Every experienced practitioner knows that preparing data for modeling is a painstaking, time-consuming process. Adding to the difficulty is that most modelers learn the steps involved in cleaning and managing data piecemeal, often on the fly, or they develop their own ad hoc methods. This book helps simplify their task by providing a unified, systematic approach to acquiring, modeling, manipulating, cleaning, and maintaining data in R. Starting with the very basics, data scientists Samuel E. Buttrey and Lyn R. Whitaker walk readers through the entire process. From what data looks like and what it should look like, they progress through all the steps involved in getting data ready for modeling. They describe best practices for acquiring data from numerous sources; explore key issues in data handling, including text/regular expressions, big data, paralTable of ContentsAbout the Authors xv Preface xvii Acknowledgments xix About the CompanionWebsite xxi 1 R 1 1.1 Introduction 1 1.1.1 What Is R? 1 1.1.2 Who Uses R and Why? 2 1.1.3 Acquiring and Installing R 2 1.1.4 Starting and Quitting R 3 1.2 Data 3 1.2.1 Acquiring Data 3 1.2.2 Cleaning Data 4 1.2.3 The Goal of Data Cleaning 4 1.2.4 Making YourWork Reproducible 5 1.3 The Very Basics of R 5 1.3.1 Top Ten Quick Facts You Need to Know about R 5 1.3.2 Vocabulary 8 1.3.3 Calculating and Printing in R 11 1.4 Running an R Session 12 1.4.1 Where Your Data Is Stored 13 1.4.2 Options 13 1.4.3 Scripts 14 1.4.4 R Packages 14 1.4.5 RStudio and Other GUIs 15 1.4.6 Locales and Character Sets 15 1.5 Getting Help 16 1.5.1 At the Command Line 16 1.5.2 The Online Manuals 16 1.5.3 On the Internet 17 1.5.4 Further Reading 17 1.6 How to Use This Book 17 1.6.1 Syntax and Conventions inThis Book 17 1.6.2 The Chapters 18 2 RData,Part1:Vectors 21 2.1 Vectors 21 2.1.1 Creating Vectors 21 2.1.2 Sequences 22 2.1.3 Logical Vectors 23 2.1.4 Vector Operations 24 2.1.5 Names 27 2.2 Data Types 27 2.2.1 Some Less-Common Data Types 28 2.2.2 What Type of Vector IsThis? 28 2.2.3 Converting from One Type to Another 29 2.3 Subsets of Vectors 31 2.3.1 Extracting 31 2.3.2 Vectors of Length 0 34 2.3.3 Assigning or Replacing Elements of a Vector 35 2.4 Missing Data (NA) and Other Special Values 36 2.4.1 The Effect of NAs in Expressions 37 2.4.2 Identifying and Removing or Replacing NAs 37 2.4.3 Indexing with NAs 39 2.4.4 NaN and Inf Values 40 2.4.5 NULL Values 40 2.5 The table() Function 40 2.5.1 Two- and Higher-Way Tables 42 2.5.2 Operating on Elements of a Table 42 2.6 Other Actions on Vectors 45 2.6.1 Rounding 45 2.6.2 Sorting and Ordering 45 2.6.3 Vectors as Sets 46 2.6.4 Identifying Duplicates and Matching 47 2.6.5 Finding Runs of Duplicate Values 49 2.7 Long Vectors and Big Data 50 2.8 Chapter Summary and Critical Data Handling Tools 50 3 R Data, Part 2:More Complicated Structures 53 3.1 Introduction 53 3.2 Matrices 53 3.2.1 Extracting and Assigning 54 3.2.2 Row and Column Names 56 3.2.3 Applying a Function to Rows or Columns 57 3.2.4 Missing Values in Matrices 59 3.2.5 Using a Matrix Subscript 60 3.2.6 Sparse Matrices 61 3.2.7 Three- and Higher-Way Arrays 62 3.3 Lists 62 3.3.1 Extracting and Assigning 64 3.3.2 Lists in Practice 65 3.4 Data Frames 67 3.4.1 Missing Values in Data Frames 69 3.4.2 Extracting and Assigning in Data Frames 69 3.4.3 ExtractingThings That Aren’tThere 72 3.5 Operating on Lists and Data Frames 74 3.5.1 Split, Apply, Combine 75 3.5.2 All-Numeric Data Frames 77 3.5.3 Convenience Functions 78 3.5.4 Re-Ordering, De-Duplicating, and Sampling from Data Frames 79 3.6 Date and Time Objects 80 3.6.1 Formatting Dates 80 3.6.2 Common Operations on Date Objects 82 3.6.3 Differences between Dates 83 3.6.4 Dates and Times 83 3.6.5 Creating POSIXt Objects 85 3.6.6 Mathematical Functions for Date and Times 86 3.6.7 Missing Values in Dates 88 3.6.8 Using Apply Functions with Dates and Times 89 3.7 Other Actions on Data Frames 90 3.7.1 Combining by Rows or Columns 90 3.7.2 Merging Data Frames 91 3.7.3 Comparing Two Data Frames 94 3.7.4 Viewing and Editing Data Frames Interactively 94 3.8 Handling Big Data 94 3.9 Chapter Summary and Critical Data Handling Tools 96 4 RData, Part 3: Text and Factors 99 4.1 Character Data 100 4.1.1 The length() and nchar() Functions 100 4.1.2 Tab, New-Line, Quote, and Backslash Characters 100 4.1.3 The Empty String 101 4.1.4 Substrings 102 4.1.5 Changing Case and Other Substitutions 103 4.2 Converting Numbers into Text 103 4.2.2 Scientific Notation 106 4.2.3 Discretizing a Numeric Variable 107 4.3 Constructing Character Strings: Paste in Action 109 4.3.1 Constructing Column Names 109 4.3.2 Tabulating Dates by Year and Month or Quarter Labels 111 4.3.3 Constructing Unique Keys 112 4.3.4 Constructing File and Path Names 112 4.4 Regular Expressions 112 4.4.1 Types of Regular Expressions 113 4.4.2 Tools for Regular Expressions in R 113 4.4.3 Special Characters in Regular Expressions 114 4.4.4 Examples 114 4.4.5 The regexpr() Function and Its Variants 121 4.4.6 Using Regular Expressions in Replacement 123 4.4.7 Splitting Strings at Regular Expressions 124 4.4.8 Regular Expressions versusWildcard Matching 125 4.4.9 Common Data Cleaning Tasks Using Regular Expressions 126 4.4.10 Documenting and Debugging Regular Expressions 127 4.5 UTF-8 and Other Non-ASCII Characters 128 4.5.1 Extended ASCII for Latin Alphabets 128 4.5.2 Non-Latin Alphabets 129 4.5.3 Character and String Encoding in R 130 4.6 Factors 131 4.6.1 What Is a Factor? 131 4.6.2 Factor Levels 132 4.6.3 Converting and Combining Factors 134 4.6.4 Missing Values in Factors 136 4.6.5 Factors in Data Frames 137 4.7 R Object Names and Commands as Text 137 4.7.1 R Object Names as Text 137 4.7.2 R Commands as Text 138 4.8 Chapter Summary and Critical Data Handling Tools 140 5 Writing Functions and Scripts 143 5.1 Functions 143 5.1.1 Function Arguments 144 5.1.2 Global versus Local Variables 148 5.1.3 Return Values 149 5.1.4 Creating and Editing Functions 151 5.2 Scripts and Shell Scripts 153 5.2.1 Line-by-Line Parsing 155 5.3 Error Handling and Debugging 156 5.3.1 Debugging Functions 156 5.3.2 Issuing Error andWarning Messages 158 5.3.3 Catching and Processing Errors 159 5.4 Interacting with the Operating System 161 5.4.1 File and Directory Handling 162 5.4.2 Environment Variables 162 5.5 SpeedingThings Up 163 5.5.1 Profiling 163 5.5.2 Vectorizing Functions 164 5.5.3 Other Techniques to Speed Things Up 165 5.6 Chapter Summary and Critical Data Handling Tools 167 5.6.1 Programming Style 168 5.6.2 Common Bugs 169 5.6.3 Objects, Classes, and Methods 170 6 Getting Data into and out of R 171 6.1 Reading Tabular ASCII Data into Data Frames 171 6.1.1 Files with Delimiters 172 6.1.2 Column Classes 173 6.1.3 Common Pitfalls in Reading Tables 175 6.1.4 An Example of When read.table() Fails 177 6.1.5 Other Uses of the scan() Function 181 6.1.6 Writing Delimited Files 182 6.1.7 Reading andWriting Fixed-Width Files 183 6.1.8 A Note on End-of-Line Characters 183 6.2 Reading Large, Non-Tabular, or Non-ASCII Data 184 6.2.1 Opening and Closing Files 184 6.2.2 Reading andWriting Lines 185 6.2.3 Reading andWriting UTF-8 and Other Encodings 187 6.2.4 The Null Character 187 6.2.5 Binary Data 188 6.2.6 Reading Problem Files in Action 190 6.3 Reading Data From Relational Databases 192 6.3.1 Connecting to the Database Server 193 6.3.2 Introduction to SQL 194 6.4 Handling Large Numbers of Input Files 197 6.5 Other Formats 200 6.5.1 Using the Clipboard 200 6.5.2 Reading Data from Spreadsheets 201 6.5.3 Reading Data from theWeb 203 6.5.4 Reading Data from Other Statistical Packages 208 6.6 Reading andWriting R Data Directly 209 6.7 Chapter Summary and Critical Data Handling Tools 210 7 Data Handling in Practice 213 7.1 Acquiring and Reading Data 213 7.2 Cleaning Data 214 7.3 Combining Data 216 7.3.1 Combining by Row 216 7.3.2 Combining by Column 218 7.3.3 Merging by Key 218 7.4 Transactional Data 219 7.4.1 Example of Transactional Data 219 7.4.2 Combining Tabular and Transactional Data 221 7.5 Preparing Data 225 7.6 Documentation and Reproducibility 226 7.7 The Role of Judgment 228 7.8 Data Cleaning in Action 230 7.8.1 Reading and Cleaning BedBath1.csv 231 7.8.2 Reading and Cleaning BedBath2.csv 236 7.8.3 Combining the BedBath Data Frames 238 7.8.4 Reading and Cleaning EnergyUsage.csv 239 7.8.5 Merging the BedBath and EnergyUsage Data Frames 242 7.9 Chapter Summary and Critical Data Handling Tools 245 8 Extended Exercise 247 8.1 Introduction to the Problem 247 8.1.1 The Goal 248 8.1.2 Modeling Considerations 249 8.1.3 Examples ofThings to Check 249 8.2 The Data 250 8.3 Five Important Fields 252 8.4 Loan and Application Portfolios 252 8.4.1 Layout of the Beachside Lenders Data 253 8.4.2 Layout of theWilson and Sons Data 254 8.4.3 Combining the Two Portfolios 254 8.5 Scores 256 8.5.1 Scores Layout 256 8.6 Co-borrower Scores 257 8.6.1 Co-borrower Score Examples 258 8.7 Updated KScores 259 8.7.1 Updated KScores Layout 259 8.8 Loans to Be Excluded 260 8.8.1 Sample Exclusion File 260 8.9 Response Variable 260 8.10 Assembling the Final Data Sets 262 8.10.1 Final Data Layout 262 8.10.2 Concluding Remarks 263 A Hints and Pseudocode 265 A.1 Loan Portfolios 265 A.1.1 Things to Check 266 A.2 Scores Database 267 A.2.1 Things to Check 268 A.3 Co-borrower Scores 269 A.3.1 Things to Check 270 A.4 Updated KScores 271 A.4.1 Things to Check 272 A.5 Excluder Files 272 A.5.1 Things to Check 272 A.6 Payment Matrix 273 A.6.1 Things to Check 274 A.7 Starting the Modeling Process 275 Bibliography 277 Index 279

Read more less

Book SynopsisIntroduces professionals and scientists to statistics and machine learning using the programming language R Written by and for practitioners, this book provides an overall introduction to R, focusing on tools and methods commonly used in data science, and placing emphasis on practice and business use. It covers a wide range of topics in a single volume, including big data, databases, statistical machine learning, data wrangling, data visualization, and the reporting of results. The topics covered are all important for someone with a science/math background that is looking to quickly learn several practical technologies to enter or transition to the growing field of data science. The Big R-Book for Professionals: From Data Science to Learning Machines and Reporting with R includes nine parts, starting with an introduction to the subject and followed by an overview of R and elements of statistics. The third part revolves around data, while the fourth focuseTable of ContentsForeword xxv About the Author xxvii Acknowledgements xxix Preface xxxi About the Companion Site xxxv I Introduction 1 1 The Big Picture with Kondratiev and Kardashev 3 2 The Scientific Method and Data 7 3 Conventions 11 II Starting with R and Elements of Statistics 19 4 The Basics of R 21 4.1 Getting Started with R 23 4.2 Variables 26 4.3 Data Types 28 4.3.1 The Elementary Types 28 4.3.2 Vectors 29 4.3.3 Accessing Data from a Vector 29 4.3.4 Matrices 32 4.3.5 Arrays 38 4.3.6 Lists 41 4.3.7 Factors 45 4.3.8 Data Frames 49 4.3.9 Strings or the Character-type 54 4.4 Operators 57 4.4.1 Arithmetic Operators 57 4.4.2 Relational Operators 57 4.4.3 Logical Operators 58 4.4.4 Assignment Operators 59 4.4.5 Other Operators 61 4.5 Flow Control Statements 63 4.5.1 Choices 63 4.5.2 Loops 65 4.6 Functions 69 4.6.1 Built-in Functions 69 4.6.2 Help with Functions 69 4.6.3 User-defined Functions 70 4.6.4 Changing Functions 70 4.6.5 Creating Function with Default Arguments 71 4.7 Packages 72 4.7.1 Discovering Packages in R 72 4.7.2 Managing Packages in R 73 4.8 Selected Data Interfaces 75 4.8.1 CSV Files 75 4.8.2 Excel Files 79 4.8.3 Databases 79 5 Lexical Scoping and Environments 81 5.1 Environments in R 81 5.2 Lexical Scoping in R 83 6 The Implementation of OO 87 6.1 Base Types 89 6.2 S3 Objects 91 6.2.1 Creating S3 Objects 94 6.2.2 Creating Generic Methods 96 6.2.3 Method Dispatch 97 6.2.4 Group Generic Functions 98 6.3 S4 Objects 100 6.3.1 Creating S4 Objects 100 6.3.2 Using S4 Objects 101 6.3.3 Validation of Input 105 6.3.4 Constructor functions 107 6.3.5 The Data slot 108 6.3.6 Recognising Objects, Generic Functions, and Methods 108 6.3.7 CreatingS4Generics 110 6.3.8 Method Dispatch 111 6.4 The Reference Class, refclass, RC or R5 Model 113 6.4.1 Creating RC Objects 113 6.4.2 Important Methods and Attributes 117 6.5 Conclusions about the OO Implementation 119 7 Tidy R with the Tidyverse 121 7.1 The Philosophy of the Tidyverse 121 7.2 Packages in the Tidyverse 124 7.2.1 The Core Tidyverse 124 7.2.2 The Non-core Tidyverse 125 7.3 Working with the Tidyverse 127 7.3.1 Tibbles 127 7.3.2 Piping with R 132 7.3.3 Attention Points When Using the Pipe 133 7.3.4 Advanced Piping 134 7.3.5 Conclusion 137 8 Elements of Descriptive Statistics 139 8.1 Measures of Central Tendency 139 8.1.1 Mean 139 8.1.2 The Median 142 8.1.3 The Mode 143 8.2 Measures of Variation or Spread 145 8.3 Measures of Covariation 147 8.3.1 The Pearson Correlation 147 8.3.2 The Spearman Correlation 148 8.3.3 Chi-square Tests 149 8.4 Distributions 150 8.4.1 Normal Distribution 150 8.4.2 Binomial Distribution 153 8.5 Creating an Overview of Data Characteristics 155 9 Visualisation Methods 159 9.1 Scatterplots 161 9.2 Line Graphs 163 9.3 Pie Charts 165 9.4 Bar Charts 167 9.5 Boxplots 171 9.6 Violin Plots 173 9.7 Histograms 176 9.8 Plotting Functions 179 9.9 Maps and Contour Plots 180 9.10 Heat-maps 181 9.11 Text Mining 184 9.11.1 Word Clouds 184 9.11.2 Word Associations 188 9.12 Colours in R 191 10 Time Series Analysis 197 10.1 Time Series in R 197 10.1.1 The Basics of Time Series in R 197 10.2 Forecasting 200 10.2.1 Moving Average 200 10.2.2 Seasonal Decomposition 206 11 Further Reading 211 III Data Import 213 12 A Short History of Modern Database Systems 215 13 RDBMS 219 14 SQL 223 14.1 Designing the Database 223 14.2 Building the Database Structure 226 14.2.1 Installing a RDBMS 226 14.2.2 Creating the Database 228 14.2.3 Creating the Tables and Relations 229 14.3 Adding Data to the Database 235 14.4 Querying the Database 239 14.4.1 The Basic Select Query 239 14.4.2 More Complex Queries 240 14.5 Modifying the Database Structure 244 14.6 Selected Features of SQL 249 14.6.1 Changing Data 249 14.6.2 Functions in SQL 249 15 Connecting R to an SQL Database 253 IV Data Wrangling 257 16 Anonymous Data 261 17 Data Wrangling in the tidyverse 265 17.1 Importing the Data 266 17.1.1 Importing from an SQLRDBMS 266 17.1.2 Importing Flat Files in the Tidyverse 267 17.2 Tidy Data 275 17.3 Tidying Up Data with tidyr 277 17.3.1 Splitting Tables 278 17.3.2 Convert Headers to Data 281 17.3.3 Spreading One Column Over Many 284 17.3.4 Split One Columns into Many 285 17.3.5 Merge Multiple Columns Into One 286 17.3.6 Wrong Data 287 17.4 SQL-like Functionality via dplyr 288 17.4.1 Selecting Columns 288 17.4.2 Filtering Rows 289 17.4.3 Joining 290 17.4.4 Mutating Data 293 17.4.5 Set Operations 296 17.5 String Manipulation in the tidyverse 299 17.5.1 Basic String Manipulation 300 17.5.2 Pattern Matching with Regular Expressions 302 17.6 Dates with lubridate 314 17.6.1 ISO 8601 Format 315 17.6.2 Time-zones 317 17.6.3 Extract Date and Time Components 318 17.6.4 Calculating with Date-times 319 17.7 Factors with Forcats 325 18 Dealing with Missing Data 333 18.1 Reasons for Data to be Missing 334 18.2 Methods to Handle Missing Data 336 18.2.1 Alternative Solutions to Missing Data 336 18.2.2 Predictive Mean Matching(PMM) 338 18.3 R Packages to Deal with Missing Data 339 18.3.1 mice 339 18.3.2 missForest 340 18.3.3 Hmisc 341 19 Data Binning 343 19.1 What is Binning and Why Use It 343 19.2 Tuning the Binning Procedure 347 19.3 More Complex Cases: Matrix Binning 352 19.4 Weight of Evidence and Information Value 359 19.4.1 Weight of Evidence(WOE) 359 19.4.2 Information Value(IV) 359 19.4.3 WOE and IV in R 359 20 Factoring Analysis and Principle Components 363 20.1 Principle Components Analysis (PCA) 364 20.2 Factor Analysis 368 V Modelling 373 21 Regression Models 375 21.1 Linear Regression 375 21.2 Multiple Linear Regression 379 21.2.1 Poisson Regression 379 21.2.2 Non-linear Regression 381 21.3 Performance of Regression Models 384 21.3.1 Mean Square Error (MSE) 384 21.3.2 R-Squared 384 21.3.3 Mean Average Deviation(MAD) 386 22 Classification Models 387 22.1 Logistic Regression 388 22.2 Performance of Binary Classification Models 390 22.2.1 The Confusion Matrix and Related Measures 391 22.2.2 ROC 393 22.2.3 The AUC 396 22.2.4 The Gini Coefficient 397 22.2.5 Kolmogorov-Smirnov (KS) for Logistic Regression 398 22.2.6 Finding an Optimal Cut-off 399 23 Learning Machines 405 23.1 Decision Tree 407 23.1.1 Essential Background 407 23.1.2 Important Considerations 412 23.1.3 Growing Trees with the Package rpart 414 23.1.4 Evaluating the Performance of a Decision Tree 424 23.2 Random Forest 428 23.3 Artificial Neural Networks (ANNs) 434 23.3.1 The Basics of ANNs in R 434 23.3.2 Neural Networks in R 436 23.3.3 The Work-flow to for Fitting a NN 438 23.3.4 Cross Validate the NN 444 23.4 Support Vector Machine 447 23.4.1 Fitting a SVM in R 447 23.4.2 Optimizing the SVM 449 23.5 Unsupervised Learning and Clustering 450 23.5.1 k-Means Clustering 450 23.5.2 Visualizing Clusters in Three Dimensions 462 23.5.3 Fuzzy Clustering 464 23.5.4 Hierarchical Clustering 466 23.5.5 Other Clustering Methods 468 24 Towards a Tidy Modelling Cycle with modelr 469 24.1 Adding Predictions 470 24.2 Adding Residuals 471 24.3 Bootstrapping Data 472 24.4 Other Functions of modelr 474 25 Model Validation 475 25.1 Model Quality Measures 476 25.2 Predictions and Residuals 477 25.3 Bootstrapping 479 25.3.1 Bootstrapping in Base R 479 25.3.2 Bootstrapping in the tidyverse with modelr 481 25.4 Cross-Validation 483 25.4.1 Elementary Cross Validation 483 25.4.2 Monte Carlo Cross Validation 486 25.4.3 k-Fold Cross Validation 488 25.4.4 Comparing Cross Validation Methods 489 25.5 Validation in a Broader Perspective 492 26 Labs 495 26.1 Financial Analysis with quantmod 495 26.1.1 The Basics of quantmod 495 26.1.2 Types of Data Available in quantmod 496 26.1.3 Plotting with quantmod 497 26.1.4 The quantmod Data Structure 500 26.1.5 Support Functions Supplied by quantmod 502 26.1.6 Financial Modelling in quantmod 504 27 Multi Criteria Decision Analysis (MCDA) 511 27.1 What and Why 511 27.2 General Work-flow 513 27.3 Identify the Issue at Hand: Steps 1 and 2 516 27.4 Step3: the Decision Matrix 518 27.4.1 Construct a Decision Matrix 518 27.4.2 Normalize the Decision Matrix 520 27.5 Step 4: Delete Inefficient and Unacceptable Alternatives 521 27.5.1 Unacceptable Alternatives 521 27.5.2 Dominance – Inefficient Alternatives 521 27.6 Plotting Preference Relationships 524 27.7 Step5: MCDA Methods 526 27.7.1 Examples of Non-compensatory Methods 526 27.7.2 The Weighted Sum Method(WSM) 527 27.7.3 Weighted Product Method(WPM) 530 27.7.4 ELECTRE 530 27.7.5 PROMethEE 540 27.7.6 PCA(Gaia) 553 27.7.7 Outranking Methods 557 27.7.8 Goal Programming 558 27.8 Summary MCDA 561 VI Introduction to Companies 563 28 Financial Accounting (FA) 567 28.1 The Statements of Accounts 568 28.1.1 Income Statement 568 28.1.2 Net Income: The P&L statement 568 28.1.3 Balance Sheet 569 28.2 The Value Chain 571 28.3 Further, Terminology 573 28.4 Selected Financial Ratios 575 29 Management Accounting 583 29.1 Introduction 583 29.1.1 Definition of Management Accounting (MA) 583 29.1.2 Management Information Systems (MIS) 584 29.2 Selected Methods in MA 585 29.2.1 Cost Accounting 585 29.2.2 Selected Cost Types 587 29.3 Selected Use Cases of MA 590 29.3.1 Balanced Scorecard 590 29.3.2 Key Performance Indicators (KPIs) 591 30 Asset Valuation Basics 597 30.1 Time Value of Money 598 30.1.1 Interest Basics 598 30.1.2 Specific Interest Rate Concepts 598 30.1.3 Discounting 600 30.2 Cash 601 30.3 Bonds 602 30.3.1 Features of a Bond 602 30.3.2 Valuation of Bonds 604 30.3.3 Duration 606 30.4 The Capital Asset Pricing Model (CAPM) 610 30.4.1 The CAPM Framework 610 30.4.2 The CAPM and Risk 612 30.4.3 Limitations and Shortcomings of the CAPM 612 30.5 Equities 614 30.5.1 Definition 614 30.5.2 Short History 614 30.5.3 Valuation of Equities 615 30.5.4 Absolute Value Models 616 30.5.5 Relative Value Models 625 30.5.6 Selection of Valuation Methods 630 30.5.7 Pitfalls in Company Valuation 631 30.6 Forwards and Futures 638 30.7 Options 640 30.7.1 Definitions 640 30.7.2 Commercial Aspects 642 30.7.3 Short History 643 30.7.4 Valuation of Options at Maturity 644 30.7.5 The Black and Scholes Model 649 30.7.6 The Binomial Model 654 30.7.7 Dependencies of the Option Price 660 30.7.8 The Greeks 664 30.7.9 Delta Hedging 665 30.7.10 Linear Option Strategies 667 30.7.11 Integrated Option Strategies 674 30.7.12 Exotic Options 678 30.7.13 Capital Protected Structures 680 VII Reporting 683 31 A Grammar of Graphics with ggplot2 687 31.1 TheBasicsofggplot2 688 31.2 Over-plotting 692 31.3 CaseStudyforggplot2 696 32 R Markdown 699 33 knitr and LATEX 703 34 An Automated Development Cycle 707 35 Writing and Communication Skills 709 36 Interactive Apps 713 36.1 Shiny 715 36.2 Browser Born Data Visualization 719 36.2.1 HTML-widgets 719 36.2.2 Interactive Maps with leaflet 720 36.2.3 Interactive Data Visualisation with ggvis 721 36.2.4 googleVis 723 36.3 Dashboards 725 36.3.1 The Business Case: a Diversity Dashboard 726 36.3.2 A Dashboard with flexdashboard 731 36.3.3 A Dashboard with shinydashboard 737 VIII Bigger and Faster R 741 37 Parallel Computing 743 37.1 Combine foreach and doParallel 745 37.2 Distribute Calculations over LAN with Snow 748 37.3 Using the GPU 752 37.3.1 Getting Started with gpuR 754 37.3.2 On the Importance of Memory use 757 37.3.3 Conclusions for GPU Programming 759 38 R and Big Data 761 38.1 Use a Powerful Server 763 38.1.1 Use R on a Server 763 38.1.2 Let the Database Server do the Heavy Lifting 763 38.2 Using more Memory than we have RAM 765 39 Parallelism for Big Data 767 39.1 Apache Hadoop 769 39.2 Apache Spark 771 39.2.1 Installing Spark 771 39.2.2 Running Spark 773 39.2.3 SparkR 776 39.2.4 sparklyr 788 39.2.5 SparkR or sparklyr 791 40 The Need for Speed 793 40.1 Benchmarking 794 40.2 Optimize Code 797 40.2.1 Avoid Repeating the Same 797 40.2.2 Use Vectorisation where Appropriate 797 40.2.3 Pre-allocating Memory 799 40.2.4 Use the Fastest Function 800 40.2.5 Use the Fastest Package 801 40.2.6 Be Mindful about Details 802 40.2.7 Compile Functions 804 40.2.8 Use C or C++ Code in R 806 40.2.9 Using a C++ Source File in R 809 40.2.10CallCompiledC++Functions in R 811 40.3 Profiling Code 812 40.3.1 The Package profr 813 40.3.2 The Package proftools 813 40.4 Optimize Your Computer 817 IX Appendices 819 A Create your own R Package 821 A.1 Creating the Package in the R Console 823 A.2 Update the Package Description 825 A.3 Documenting the Functionsxs 826 A.4 Loading the Package 827 A.5 Further Steps 828 B Levels of Measurement 829 B.1 Nominal Scale 829 B.2 Ordinal Scale 830 B.3 Interval Scale 831 B.4 Ratio Scale 832 C Trademark Notices 833 C.1 General Trademark Notices 834 C.2 R-Related Notices 835 C.2.1 Crediting Developers of R Packages 835 C.2.2 The R-packages used in this Book 835 D Code Not Shown in the Body of the Book 839 E Answers to Selected Questions 845 Bibliography 859 Nomenclature 869 Index 881

Read more less

Book SynopsisTable of ContentsIntroduction xvii Assessment Test xxix Answers to Assessment Test xxxv Part I Introduction 1 Chapter 1 AWS AI ML Stack 3 Amazon Rekognition 4 Image and Video Operations 6 Amazon Textract 10 Sync and Async APIs 11 Amazon Transcribe 13 Transcribe Features 13 Transcribe Medical 14 Amazon Translate 15 Amazon Translate Features 16 Amazon Polly 17 Amazon Lex 19 Lex Concepts 19 Amazon Kendra 21 How Kendra Works 22 Amazon Personalize 23 Amazon Forecast 27 Forecasting Metrics 30 Amazon Comprehend 32 Amazon CodeGuru 33 Amazon Augmented AI 34 Amazon SageMaker 35 Analyzing and Preprocessing Data 36 Training 39 Model Inference 40 AWS Machine Learning Devices 42 Summary 43 Exam Essentials 43 Review Questions 44 Chapter 2 Supporting Services from the AWS Stack 49 Storage 50 Amazon S3 50 Amazon EFS 52 Amazon FSx for Lustre 52 Data Versioning 53 Amazon VPC 54 AWS Lambda 56 AWS Step Functions 59 AWS RoboMaker 60 Summary 62 Exam Essentials 62 Review Questions 63 Part II Phases of Machine Learning Workloads 67 Chapter 3 Business Understanding 69 Phases of ML Workloads 70 Business Problem Identification 71 Summary 72 Exam Essentials 73 Review Questions 74 Chapter 4 Framing a Machine Learning Problem 77 ML Problem Framing 78 Recommended Practices 80 Summary 81 Exam Essentials 81 Review Questions 82 Chapter 5 Data Collection 85 Basic Data Concepts 86 Data Repositories 88 Data Migration to AWS 89 Batch Data Collection 89 Streaming Data Collection 92 Summary 96 Exam Essentials 96 Review Questions 98 Chapter 6 Data Preparation 101 Data Preparation Tools 102 SageMaker Ground Truth 102 Amazon EMR 104 Amazon SageMaker Processing 105 AWS Glue 105 Amazon Athena 107 Redshift Spectrum 107 Summary 107 Exam Essentials 107 Review Questions 109 Chapter 7 Feature Engineering 113 Feature Engineering Concepts 114 Feature Engineering for Tabular Data 114 Feature Engineering for Unstructured and Time Series Data 119 Feature Engineering Tools on AWS 120 Summary 121 Exam Essentials 121 Review Questions 123 Chapter 8 Model Training 127 Common ML Algorithms 128 Supervised Machine Learning 129 Textual Data 138 Image Analysis 141 Unsupervised Machine Learning 142 Reinforcement Learning 146 Local Training and Testing 147 Remote Training 149 Distributed Training 150 Monitoring Training Jobs 154 Amazon CloudWatch 155 AWS CloudTrail 155 Amazon Event Bridge 158 Debugging Training Jobs 158 Hyperparameter Optimization 159 Summary 162 Exam Essentials 162 Review Questions 164 Chapter 9 Model Evaluation 167 Experiment Management 168 Metrics and Visualization 169 Metrics in AWS AI/ML Services 173 Summary 174 Exam Essentials 175 Review Questions 176 Chapter 10 Model Deployment and Inference 181 Deployment for AI Services 182 Deployment for Amazon SageMaker 184 SageMaker Hosting: Under the Hood 184 Advanced Deployment Topics 187 Autoscaling Endpoints 187 Deployment Strategies 188 Testing Strategies 190 Summary 191 Exam Essentials 191 Review Questions 192 Chapter 11 Application Integration 195 Integration with On-Premises Systems 196 Integration with Cloud Systems 198 Integration with Front-End Systems 200 Summary 200 Exam Essentials 201 Review Questions 202 Part III Machine Learning Well-Architected Lens 205 Chapter 12 Operational Excellence Pillar for ML 207 Operational Excellence on AWS 208 Everything as Code 209 Continuous Integration and Continuous Delivery 210 Continuous Monitoring 213 Continuous Improvement 214 Summary 215 Exam Essentials 215 Review Questions 217 Chapter 13 Security Pillar 221 Security and AWS 222 Data Protection 223 Isolation of Compute 224 Fine-Grained Access Controls 225 Audit and Logging 226 Compliance Scope 227 Secure SageMaker Environments 228 Authentication and Authorization 228 Data Protection 231 Network Isolation 232 Logging and Monitoring 233 Compliance Scope 235 AI Services Security 235 Summary 236 Exam Essentials 236 Review Questions 238 Chapter 14 Reliability Pillar 241 Reliability on AWS 242 Change Management for ML 242 Failure Management for ML 245 Summary 246 Exam Essentials 246 Review Questions 247 Chapter 15 Performance Efficiency Pillar for ML 251 Performance Efficiency for ML on AWS 252 Selection 253 Review 254 Monitoring 255 Trade-offs 256 Summary 257 Exam Essentials 257 Review Questions 258 Chapter 16 Cost Optimization Pillar for ML 261 Common Design Principles 262 Cost Optimization for ML Workloads 263 Design Principles 263 Common Cost Optimization Strategies 264 Summary 266 Exam Essentials 266 Review Questions 267 Chapter 17 Recent Updates in the AWS AI/ML Stack 271 New Services and Features Related to AI Services 272 New Services 272 New Features of Existing Services 275 New Features Related to Amazon SageMaker 279 Amazon SageMaker Studio 279 Amazon SageMaker Data Wrangler 279 Amazon SageMaker Feature Store 280 Amazon SageMaker Clarify 281 Amazon SageMaker Autopilot 282 Amazon SageMaker JumpStart 283 Amazon SageMaker Debugger 283 Amazon SageMaker Distributed Training Libraries 284 Amazon SageMaker Pipelines and Projects 284 Amazon SageMaker Model Monitor 284 Amazon SageMaker Edge Manager 285 Amazon SageMaker Asynchronous Inference 285 Summary 285 Exam Essentials 285 Appendix Answers to the Review Questions 287 Chapter 1: AWS AI ML Stack 288 Chapter 2: Supporting Services from the AWS Stack 289 Chapter 3: Business Understanding 290 Chapter 4: Framing a Machine Learning Problem 291 Chapter 5: Data Collection 291 Chapter 6: Data Preparation 292 Chapter 7: Feature Engineering 293 Chapter 8: Model Training 294 Chapter 9: Model Evaluation 295 Chapter 10: Model Deployment and Inference 295 Chapter 11: Application Integration 296 Chapter 12: Operational Excellence Pillar for ML 297 Chapter 13: Security Pillar 298 Chapter 14: Reliability Pillar 298 Chapter 15: Performance Efficiency Pillar for ML 299 Chapter 16: Cost Optimization Pillar for ML 300 Index 303

Read more less

Book SynopsisTable of ContentsForeword xv Introduction xix Chapter 1: Do You Want to Be Part of the Future? 1 Business at the Speed of AI 2 Follow Me, Follow Me 4 In AI, We Overtrust 6 Area 52 Ramblings 10 I’ll Do It 12 Adversarial Attacks Are Happening 16 ML Systems Don’t Jiggle-Jiggle; They Fold 19 Never Tell Me the Odds 22 AI’s Achilles’ Heel 25 Chapter 2: Salt, Tape, and Split-Second Phantoms 29 Challenge Accepted 30 When Expectation Meets Reality 35 Color Me Blind 39 Translation Fails 42 Attacking AI Systems via Fails 44 Autonomous Trap 001 48 Common Corruption 51 Chapter 3: Subtle, Specific, and Ever-Present 55 Intriguing Properties of Neural Networks 57 They Are Everywhere 60 Research Disciplines Collide 62 Blame Canada 66 The Intelligent Wiggle-Jiggle 71 Bargain-Bin Models Will Do 75 For Whom the Adversarial Example Bell Tolls 79 Chapter 4: Here’s Something I Found on the Web 85 Bad Data = Big Problem 87 Your AI Is Powered by Ghost Workers 88 Your AI Is Powered by Vampire Novels 91 Don’t Believe Everything You Read on the Internet 94 Poisoning the Well 96 The Higher You Climb, the Harder You Fall 104 Chapter 5: Can You Keep a Secret? 107 Why Is Defending Against Adversarial Attacks Hard? 108 Masking Is Important 111 Because It Is Possible 115 Masking Alone Is Not Good Enough 118 An Average Concerned Citizen 119 Security by Obscurity Has Limited Benefit 124 The Opportunity Is Great; the Threat Is Real; the Approach Must Be Bold 125 Swiss Cheese 130 Chapter 6: Sailing for Adventure on the Deep Blue Sea 133 Why Be Securin’ AI Systems So Blasted Hard? An Economics Perspective, Me Hearties! 136 Tis a Sign, Me Mateys 141 Here Be the Most Crucial AI Law Ye’ve Nary Heard Tell Of! 144 Lies, Accursed Lies, and Explanations! 146 No Free Grub 148 Whatcha measure be whatcha get! 151 Who Be Reapin’ the Benefits? 153 Cargo Cult Science 155 Chapter 7: The Big One 159 This Looks Futuristic 161 By All Means, Move at a Glacial Pace; You Know How That Thrills Me 163 Waiting for the Big One 166 Software, All the Way Down 169 The Aftermath 172 Race to AI Safety 173 Happy Story 176 In Medias Res 178 Big-Picture Questions 181 Acknowledgments 185 Index 189

Read more less

Book Synopsis Solve SEO problems using data science. This hands-on book is packed with Python code and data science techniques to help you generate data-driven recommendations and automate the SEO workload. This book is a practical, modern introduction to data science in the SEO context using Python. With social media, mobile, changing search engine algorithms, and ever-increasing expectations of users for super web experiences, too much data is generated for an SEO professional to make sense of in spreadsheets. For any modern-day SEO professional to succeed, it is relevant to find an alternate solution, and data science equips SEOs to grasp the issue at hand and solve it. From machine learning to Natural Language Processing (NLP) techniques, Data-Driven SEO with Python provides tried and tested techniques with full explanations for solving both everyday and complex SEO problems. This book is ideal for SEO professionals who want to take their industry skiTable of ContentsData Driven SEO with PythonChapter 1: Meeting the Challenges of SEO with Data1.1 Agents of change in SEO1.2 The Pillars of SEO Strategy1.3 Installing Python1.4 Using Python for SEOChapter 2: Keyword Research2.1 Data Sources2.2 Google Search Console2.4 Google Trends2.5 Google Suggest2.6 Competitor Analytics2.7 SERPsChapter 3: Technical3.1 Improving CTRs3.2 Allocate keywords to pages based on the copy3.3 Allocating parent nodes to the orphaned URLs3.4 Improve interlinking based on copy3.5 Automate Technical AuditsChapter 4: Content & UX4.1 Content that best satisfies the user query4.2 Splitting and merging URLs4.3 Content Strategy: Planning landing page content Chapter 5: Authority5.1 A little SEO history5.1 The source of authority5.2 Finding good linksChapter 6: Competitors6.1 Defining the problem6.2 Data Strategy6.3 Data Sources6.4 Selecting Your Competitors6.5 Get Features6.6 Explore, Clean and Transform6.7 Modelling The SERPS6.8 Evaluating your Model6.9 ActivationChapter 7: Experiments7.1 How experiments fit into the SEO process7.2 Generating Hypotheses7.3 Experiment Design7.4 Running your experiment7.5 Experiment EvaluationChapter 8: Dashboards8.1 Use a Data Layer8.2 Extract, Transform and Load (ETL)8.3 Transform8.4 Querying the Data Warehouse (DW)8.5 Visualization8.6 Making Future ForecastsChapter 9: Site Migrations and Relaunches9.1 Data sources9.2 Establishing the Impact9.3 Segmenting the URLs9.4 Legacy Site URLs9.5 Priority9.6 RoadmapChapter 10: Google Updates10.1 Data sources10.2 Winners and Losers10.3 Quantifying the Impact10.4 Search Intent10.5 Unique URLs10.6 RecommendationsChapter 11: The Future of SEO11.1 Automation11.2 Your journey to SEO science11.3 Suggest resourcesAppendix: CodeGlossaryIndex

Read more less

Book SynopsisUpdated to emphasize new features in Spark 2.4., this second edition shows data engineers and scientists why structure and unification in Spark matters. Specifically, this book explains how to perform simple and complex data analytics and employ machine-learning algorithms.

Read more less

Book SynopsisThis updated second edition describes the intuition behind deep learning innovations without jargon or complexity. By the end of this book, Python-proficient programmers, software engineering professionals, and computer science majors will be able to re-implement these breakthroughs on their own.

Read more less