Machine learning Books
World Scientific Publishing Co Pte Ltd Machine Learning With Python: Theory And
Book SynopsisMachine Learning (ML) has become a very important area of research widely used in various industries.This compendium introduces the basic concepts, fundamental theories, essential computational techniques, codes, and applications related to ML models. With a strong foundation, one can comfortably learn related topics, methods, and algorithms. Most importantly, readers with strong fundamentals can even develop innovative and more effective machine models for his/her problems. The book is written to achieve this goal.The useful reference text benefits professionals, academics, researchers, graduate and undergraduate students in AI, ML and neural networks.
£128.25
World Scientific Publishing Co Pte Ltd Machine Learning In Bioinformatics Of Protein
Book SynopsisMachine Learning in Bioinformatics of Protein Sequences guides readers around the rapidly advancing world of cutting-edge machine learning applications in the protein bioinformatics field. Edited by bioinformatics expert, Dr Lukasz Kurgan, and with contributions by a dozen of accomplished researchers, this book provides a holistic view of the structural bioinformatics by covering a broad spectrum of algorithms, databases and software resources for the efficient and accurate prediction and characterization of functional and structural aspects of proteins. It spotlights key advances which include deep neural networks, natural language processing-based sequence embedding and covers a wide range of predictions which comprise of tertiary structure, secondary structure, residue contacts, intrinsic disorder, protein, peptide and nucleic acids-binding sites, hotspots, post-translational modification sites, and protein function. This volume is loaded with practical information that identifies and describes leading predictive tools, useful databases, webservers, and modern software platforms for the development of novel predictive tools.
£112.50
World Scientific Publishing Co Pte Ltd Adaptive Enterprise Architecture As Information:
Book SynopsisThis compendium discusses the adaptive enterprise architecture (AEA) as information to support decisions and actions for desired efficiency and innovation (outcomes and impacts). This comprehensive information-driven approach uses data, analytics, and intelligence (AI/ML) for architecting intelligent enterprises.The unique reference text includes practical artefacts and vivid examples based on both practice and research. It benefits chief information officers, chief data officers, chief enterprise architects, enterprise architects, business architects, information architects, data architects, and anyone who has an interest in adaptive and digital enterprise architecture.
£76.00
World Scientific Publishing Co Pte Ltd Artificial Intelligence For Science: A Deep
Book SynopsisThis unique collection introduces AI, Machine Learning (ML), and deep neural network technologies leading to scientific discovery from the datasets generated both by supercomputer simulation and by modern experimental facilities.Huge quantities of experimental data come from many sources — telescopes, satellites, gene sequencers, accelerators, and electron microscopes, including international facilities such as the Large Hadron Collider (LHC) at CERN in Geneva and the ITER Tokamak in France. These sources generate many petabytes moving to exabytes of data per year. Extracting scientific insights from these data is a major challenge for scientists, for whom the latest AI developments will be essential.The timely handbook benefits professionals, researchers, academics, and students in all fields of science and engineering as well as AI, ML, and neural networks. Further, the vision evident in this book inspires all those who influence or are influenced by scientific progress.
£121.50
World Scientific Publishing Co Pte Ltd Deep Learning Applications: In Computer Vision,
Book SynopsisThis book proposes various deep learning models featuring how deep learning algorithms have been applied and used in real-life settings. The complexity of real-world scenarios and constraints imposed by the environment, together with budgetary and resource limitations, have posed great challenges to engineers and developers alike, to come up with solutions to meet these demands. This book presents case studies undertaken by its contributors to overcome these problems. These studies can be used as references for designers when applying deep learning in solving real-world problems in the areas of vision, signals, and networks.The contents of this book are divided into three parts. In the first part, AI vision applications in plant disease diagnostics, PM2.5 concentration estimation, surface defect detection, and ship plate identification, are featured. The second part introduces deep learning applications in signal processing; such as time series classification, broad-learning based signal modulation recognition, and graph neural network (GNN) based modulation recognition. Finally, the last section of the book reports on graph embedding applications and GNN in AI for networks; such as an end-to-end graph embedding method for dispute detection, an autonomous System-GNN architecture to infer the relationship between Apache software, a Ponzi scheme detection framework to identify and detect Ponzi schemes, and a GNN application to predict molecular biological activities.
£90.00
World Scientific Publishing Co Pte Ltd Machine Learning, Multi Agent And Cyber Physical
Book SynopsisFLINS, an acronym originally for Fuzzy Logic and Intelligent Technologies in Nuclear Science, was inaugurated by Prof. Da Ruan of the Belgian Nuclear Research Center (SCK·CEN) in 1994 with the purpose of providing PhD and Postdoc researchers with a platform to present their research ideas in fuzzy logic and artificial intelligence. For more than 28 years, FLINS has been expanded to include research in both theoretical and practical development of computational intelligent systems.With this successful conference series: FLINS1994 and FLINS1996 in Mol, FLINS1998 in Antwerp, FLINS2000 in Bruges, FLINS2002 in Gent, FLINS2004 in Blankenberge, FLINS2006 in Genova, FLINS2008 in Marid, FLINS2010 in Chengdu, FLINS2012 in Istanbul, FLINS2014 in Juan Pesoa, FLINS2016 in Roubaix, FLINS2018 in Belfast and FLINS2020 in Cologne, FLINS2022 was organized by Nankai University, and co-organized by Southwest Jiaotong University, University of Technology Sydney and Ecole Nationale Supérieure des Arts et Industries Textiles of University of Lille. This unique international research collaboration has provided researchers with a platform to share and exchange ideas on state-of-art development in machine learning, multi agent and cyber physical systems.Following the wishes of Prof. Da Ruan, FLINS2022 offered an international platform that brought together mathematicians, computer scientists, and engineers who are actively involved in machine learning, intelligent systems, data analysis, knowledge engineering and their applications, to share their latest innovations and developments, exchange notes on the state-of-the-art research ideas, especially in the areas of industrial microgrids, intelligent wearable systems, sustainable development, logistics, supply chain and production optimization, evaluation systems and performance analysis, as well as risk and security management, that have now become part and parcel of Fuzzy Logic and Intelligent Technologies in Nuclear Science.This FLINS2022 Proceedings has selected 78 conference papers that cover the following seven areas of interests:
£157.50
World Scientific Publishing Company Lecture Notes In Deep Learning Theoretical
Book Synopsis
£80.00
World Scientific Publishing Company Lecture Notes In Deep Learning Theoretical
Book Synopsis
£42.75
World Scientific Publishing Company Deep Learning For 3d Vision Algorithms And
Book Synopsis
£130.50
World Scientific Publishing Company Towards Human Brain Inspired Lifelong Learning
Book Synopsis
£85.50
World Scientific Publishing Company Federated Learning Techniques and Its Application
Book Synopsis
£76.00
Springer Verlag, Singapore Machine Learning
Book SynopsisMachine Learning, a vital and core area of artificial intelligence (AI), is propelling the AI field ever further and making it one of the most compelling areas of computer science research. This textbook offers a comprehensive and unbiased introduction to almost all aspects of machine learning, from the fundamentals to advanced topics. It consists of 16 chapters divided into three parts: Part 1 (Chapters 1-3) introduces the fundamentals of machine learning, including terminology, basic principles, evaluation, and linear models; Part 2 (Chapters 4-10) presents classic and commonly used machine learning methods, such as decision trees, neural networks, support vector machines, Bayesian classifiers, ensemble methods, clustering, dimension reduction and metric learning; Part 3 (Chapters 11-16) introduces some advanced topics, covering feature selection and sparse learning, computational learning theory, semi-supervised learning, probabilistic graphical models, rule learning, and reinforcement learning. Each chapter includes exercises and further reading, so that readers can explore areas of interest. The book can be used as an undergraduate or postgraduate textbook for computer science, computer engineering, electrical engineering, data science, and related majors. It is also a useful reference resource for researchers and practitioners of machine learning.Trade Review“The book is full of cross-references, making the reader well aware of tight interconnections between many of the different approaches and methods. … the book is written in a very comprehensible and readable way. Its comprehensibility is further encreased through frequent marginal notes and through consistently illustrating all presented kinds of methods using the same toy example, and through historical notes to all addressed areas … the book explains also several quite advanced subjects … .” (Martin Holeňa, zbMATH 1479.68001, 2022)Table of Contents1 Introduction.- 2 Model Selection and Evaluation.- 3 Linear Models.- 4 Decision Trees.- 5 Neural Networks.- 6 Support Vector Machine.- 7 Bayes Classifiers.- 8 Ensemble Learning.- 9 Clustering.- 10 Dimensionality Reduction and Metric Learning.- 11 Feature Selection and Sparse Learning.- 12 Computational Learning Theory.- 13 Semi-Supervised Learning.- 14 Probabilistic Graphical Models.- 15 Rule Learning.- 16 Reinforcement Learning.
£49.49
Springer Verlag, Singapore Advanced Machine Learning Technologies and
Book SynopsisThis book presents the refereed proceedings of the 5th International Conference on Advanced Machine Learning Technologies and Applications (AMLTA 2020), held at Manipal University Jaipur, India, on February 13 – 15, 2020, and organized in collaboration with the Scientific Research Group in Egypt (SRGE). The papers cover current research in machine learning, big data, Internet of Things, biomedical engineering, fuzzy logic and security, as well as intelligence swarms and optimization. Table of ContentsSegregating and Recognizing Human Actions from Video Footages using LRCN Technique.- Fall Alert: A Novel Approach to Detect Fall.- Evaluation of Automatic Text Visualization Systems: A Case Study.- Face Recognition Based Attendance System using Real Time Computer Vision Algorithms.- The Impact of Knowledge Management Adoption on the Government Sector’s Performance: The Case of Bahrain.- Video Surveillance for the Crime Detection using Features.- Real-time Neural-net Driven Optimized Inverse-kinematics for a Robotic Manipulator.- A Deep Learning Technique to Countermeasure Video Based Presentation Attacks.- Optimization of Loss Functions for Predictive Soil Mapping.- Natural Language Information Extraction through Non Factoid Question and Answering System.- An Enhanced Differential Evolution Algorithm with New Environmental-based Parameters for Solving Optimization Problems.- Reactive Power Optimization Approach based on Chaotic Particle Swarm Optimization.- Data Mining Model for Better Admissions in Higher Educational Institutions (HEIs) – A Case Study of Bahrain.- The Effectiveness of Renewable Energies Projects in Kuwait - PAAET Solar Energy Project.- Skin Lesion Analyser: An Efficient Seven-Way Multi-Class Skin Cancer Classification Using Mobile Net.- Real-Time Object Detection in Remote Sensing Images using Deep Learning.- Malaria Detection using Convolutional Neural Network.- Drone-Based Face Recognition using Deep Learning.- Traffic Sign Recognition for Self-Driving Cars with Deep Learning.- Identifying the Association Rule to Determine the Possibilities of Cardio Vascular Diseases(CVD).- Prediction of Service Level Agreement Violation in Cloud Computing using Bayesian Regularization.- A New Methodology for Language Identification in Social Media Code-mixed Text.- Detecting Influencers in Social Networks Through Machine Learning Techniques.- Application and Analysis of K-Means Algorithms on a Decision Support Framework for Municipal Solid Waste Management.- Android Rogue Application Detection using Image Resemblance and Reduced LDA.- An Indexed Non-Probability Skyline Query Processing Framework for Uncertain Data.- Analysis of Operational Control Mode of Intelligent Distribution Grids with Multi-microgrid.- Technical Present Situation based on Micro Grid Operation Control.- Skin Lesion Classification: A Transfer Learning Approach Using Efficient Nets.- Change Footprint Pattern Analysis of Crime Hotspot of Indian Districts.- Itemset Mining based Episode Profiling of Terrorist Attacks using Weighted Ontology.- Enabling Technologies in Banking Industry, Regulatory Technology RegTech and Money Laundering Prevention.- A Cognitive Knowledge Base for Learning Disabilities using Concept Analysis.- Native Monkey Detection using Deep Convolution Neural Network.- Evaluation and Summarization of Student Feedbacks Using Sentiment Analysis.- Predicting Competitive Weight Lifting Performance using Regression and Tree-based Algorithms.- Predicting the Primary Dominant Personality Trait of Perceived Leaders by Mapping Linguistic Cues from Social Media Data onto the Big-Five Model.- Analysis of Users behaviour on Micro Blogging Site using a Topic.- Machine Learning Techniques for Short Term Forecasting of Wind Power Generation.- Integrated Process Management System of Smart Substation Secondary Side based on Practical Scheme.- Research on Forms and Strategies of Alternative Energy Achieved.- Lightweight Access Control Algorithm for Internet of Things.- Named Entity Recognition for Legal Documents.- Visual Speech Processing and Recognition.- Predictive Analytics for Cardiovascular Disease Diagnosis using Machine Learning Techniques.- A Novel Approach for Smart Health Care Recommender System.- Heart Disorder Prognosis employing KNN, ANN, ID3 and SVM.- IoT based Home Security System with Wireless Communication.- Implementation of Internet of Things IoT in Small Business Industry: Case of Bahrain.- A Comparative Study of Model-Free Reinforcement Learning Approaches.- Location Aware Security System for Smart Cities using IoT.- An Assessment Study of Gait Biometric Recognition using Machine Learning.- A Study on Risk Management Practices in Online Banking in Bahrain.- Deep Learning Techniques: An Overview.- A Multilayer Deep Learning Framework For Auto-Content Tagging.- Case Based Reasoning (CBR) based Anemia Severity Detection System (ASDS) Using Machine Learning Algorithm.- ECG Signal Analysis, Diagnosis and Transmission.- The Effect of Real-Time Feedback on Consumer’s Behaviour in the Energy Management Sector: Empirical study.- Synchronization Control in Fractional Discrete-Time Systems with Chaotic Hidden Attractors.- Employment of Cryptographic Modus Operandi based on Trigonometric Algorithm and Resistor Color Code.- Experimental & Dimensional Analysis Approach for Human Energy Required In Wood Chipping Process.- Impact of High-k gate dielectric and Workfunctions Variation on Electrical Characteristics of VeSFET.- Correlating Personality Traits to Different Aspects of Facebook Usage.- Fractional Order control of a Fuel Cell-boost Converter System.- Battery Pack Construction Scheme based on UPS System Reliability.- Study on Land Compensation for High Voltage Transmission Lines in Power Grid based on Easement.- Study on the Terrain of Power Network Construction Expropriation and Legal Risk Prevention.
£224.99
Springer Verlag, Singapore Deep Reinforcement Learning: Fundamentals, Research and Applications
Book SynopsisDeep reinforcement learning (DRL) is the combination of reinforcement learning (RL) and deep learning. It has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine, and famously contributed to the success of AlphaGo. Furthermore, it opens up numerous new applications in domains such as healthcare, robotics, smart grids and finance. Divided into three main parts, this book provides a comprehensive and self-contained introduction to DRL. The first part introduces the foundations of deep learning, reinforcement learning (RL) and widely used deep RL methods and discusses their implementation. The second part covers selected DRL research topics, which are useful for those wanting to specialize in DRL research. To help readers gain a deep understanding of DRL and quickly apply the techniques in practice, the third part presents mass applications, such as the intelligent transportation system and learning to run, with detailed explanations. The book is intended for computer science students, both undergraduate and postgraduate, who would like to learn DRL from scratch, practice its implementation, and explore the research topics. It also appeals to engineers and practitioners who do not have strong machine learning background, but want to quickly understand how DRL works and use the techniques in their applications.Table of Contents
£132.99
Springer Verlag, Singapore Statistical Learning with Math and Python: 100
Book SynopsisThe most crucial ability for machine learning and data science is mathematical logic for grasping their essence rather than knowledge and experience. This textbook approaches the essence of machine learning and data science by considering math problems and building Python programs. As the preliminary part, Chapter 1 provides a concise introduction to linear algebra, which will help novices read further to the following main chapters. Those succeeding chapters present essential topics in statistical learning: linear regression, classification, resampling, information criteria, regularization, nonlinear regression, decision trees, support vector machines, and unsupervised learning. Each chapter mathematically formulates and solves machine learning problems and builds the programs. The body of a chapter is accompanied by proofs and programs in an appendix, with exercises at the end of the chapter. Because the book is carefully organized to provide the solutions to the exercises in each chapter, readers can solve the total of 100 exercises by simply following the contents of each chapter. This textbook is suitable for an undergraduate or graduate course consisting of about 12 lectures. Written in an easy-to-follow and self-contained style, this book will also be perfect material for independent learning.Table of ContentsChapter 1: Linear Algebra.- Chapter 2: Linear Regression.- Chapter 3: Classification.- Chapter 4: Resampling.- Chapter 5: Information Criteria.- Chapter 6: Regularization.- Chapter 7: Nonlinear Regression.- Chapter 8: Decision Trees.- Chapter 9: Support Vector Machine.- Chapter 10: Unsupervised Learning.
£26.99
Springer Verlag, Singapore Sparse Estimation with Math and R: 100 Exercises
Book SynopsisThe most crucial ability for machine learning and data science is mathematical logic for grasping their essence rather than knowledge and experience. This textbook approaches the essence of sparse estimation by considering math problems and building R programs. Each chapter introduces the notion of sparsity and provides procedures followed by mathematical derivations and source programs with examples of execution. To maximize readers’ insights into sparsity, mathematical proofs are presented for almost all propositions, and programs are described without depending on any packages. The book is carefully organized to provide the solutions to the exercises in each chapter so that readers can solve the total of 100 exercises by simply following the contents of each chapter.This textbook is suitable for an undergraduate or graduate course consisting of about 15 lectures (90 mins each). Written in an easy-to-follow and self-contained style, this book will also be perfect material for independent learning by data scientists, machine learning engineers, and researchers interested in linear regression, generalized linear lasso, group lasso, fused lasso, graphical models, matrix decomposition, and multivariate analysis.This book is one of a series of textbooks in machine learning by the same author. Other titles are: - Statistical Learning with Math and R (https://www.springer.com/gp/book/9789811575679) - Statistical Learning with Math and Python (https://www.springer.com/gp/book/9789811578762) - Sparse Estimation with Math and PythonTable of ContentsChapter 1: Linear Regression.- Chapter 2: Generalized Linear Regression.- Chapter 3: Group Lasso.- Chapter 4: Fused Lasso.- Chapter 5: Graphical Model.- Chapter 6: Matrix Decomposition.- Chapter 7: Multivariate Analysis.
£26.99
Springer Verlag, Singapore Applications of Artificial Intelligence and
Book SynopsisThe book presents a collection of peer-reviewed articles from the International Conference on Advances and Applications of Artificial Intelligence and Machine Learning - ICAAAIML 2020. The book covers research in artificial intelligence, machine learning, and deep learning applications in healthcare, agriculture, business, and security. This volume contains research papers from academicians, researchers as well as students. There are also papers on core concepts of computer networks, intelligent system design and deployment, real-time systems, wireless sensor networks, sensors and sensor nodes, software engineering, and image processing. This book will be a valuable resource for students, academics, and practitioners in the industry working on AI applications.Table of Contents
£161.99
Springer Verlag, Singapore Renewable Energy Optimization, Planning and
Book SynopsisThis book gathers selected high-quality research papers presented at International Conference on Renewable Technologies in Engineering (ICRTE 2021) organized by Manav Rachna International Institute of Research & Studies, Faridabad, Haryana, India, during 15–16 April 2021. The book includes conference papers on the theme “Computational Techniques for Renewable Energy Optimization”, which aims to bring together leading academic scientists, researchers and research scholars to exchange and share their experiences and research results on all aspects of renewable energy integration, planning, control and optimization. It also provides a premier interdisciplinary platform for researchers, practitioners and educators to present and discuss the most recent innovations, trends and concerns as well as practical challenges encountered and solutions adopted in the fields of renewable energy and resources.Table of ContentsChapter 1. A Review on Power Quality İmprovement of Grid Connected PV With Lithium-ion and Super Capacitor Based Hybrid Energy Storage System Using a New Control Strategy.- Chapter 2. Influence of Alternative Fuels on Exhaust Emissions of IC Engine-A Review.- Chapter 3. Hybrid Energy System For An Academic Institution: A Case Study.- Chapter 4. Challenges to Mini-Grids: An alternative to Rural Electrification.- Chapter 5. Comparative Analysis of Family of Luo Converter for Renewable Energy Applications.- Chapter 6. Design and modeling of L-shape piezoelectric energy harvester for powering Deep Brain Stimulation System.- Chapter 7. Solar Irradiation Forecasting by Long-Short Term Memory using Different Training Algorithms.- Chapter 8. Forecasting of Wind Speed by Using Deep Learning for Optimal Use of the Energy Produced by Wind Farms.- Chapter 9. Analysis of Predictive Current Control Technique in Wind EnergyConversion System.- Chapter 10. Genetic Algorithm based Intelligent Control Strategy for Multi Input Multi Output DC-DC Converter.- Chapter 11. Wavelet Transform Based Comparative Analysis of Wind Speed Forecasting Techniques.- Chapter 12. Maximization of Energy Production from Sholayar Hydropower Plant in India.- Chapter 13. Cuk based Single Phase Inverter Design for PV Array Systems.- Chapter 14. Support Vector Machine based Forecasting for Renewable Energy Systems.- Chapter 15. Efficiency Improvement of PV Panel Using PCM Cooling Technique.- Chapter 16. Parametric Identification AlgorithmUsing Chebyshev−Laguerre Functions.- Chapter 17. Analysis of Piezoelectric Energy harvesting schemes and a proposition for state-of-the-art approach in Hydro-electric power generation.
£179.99
Springer Verlag, Singapore Artificial Intelligence for Automated Pricing
Book SynopsisThis book highlights artificial intelligence algorithms used in implementation of automated pricing. It presents the process for building automated pricing models from crawl data, preprocessed data to implement models, and their applications. The book also focuses on machine learning and deep learning methods for pricing, including from regression methods to hybrid and ensemble methods. The computational experiments are presented to illustrate the pricing processes and models.Table of Contents1. Pricing based on product descriptions: problem, data, and methods.- 2. Extract product data from descriptions by NLP techniques.- 3. Segmentation and Quantity the qualify features.- 4. Pricing prediction using machine learning and ensemble methods.- 5. Applications & Discussions.
£52.24
Springer Verlag, Singapore Mathematical Modeling, Computational Intelligence
Book SynopsisThis book presents new knowledge and recent developments in all aspects of computational techniques, mathematical modeling, energy systems, and applications of fuzzy sets and intelligent computing. The book is a collection of best selected research papers presented at the Second International Conference on “Mathematical Modeling, Computational Intelligence Techniques and Renewable Energy (MMCITRE 2021),” organized by the Department of Mathematics, Pandit Deendayal Petroleum University, in association with Forum for Interdisciplinary Mathematics. The book provides innovative works of researchers, academicians, and students in the area of interdisciplinary mathematics, statistics, computational intelligence, and renewable energy.Table of ContentsStrongly Prime Radicals and S-primary Ideals in Posets.- Association Schemes over Some Finite Group Rings.- Rings whose nonunits are multiple of unit and strongly nilpotent element.- Improved Lower Bounds on Second Order Nonlinearities of Cubic Boolean Functions.- Ces`aro-Riesz Product Summability φ − |C1R; δ|q Factor for an Infinite Series.- Ostrowski’s Type Inequalities with Exponentially Convex Functions and its Applications
£161.99
Springer Verlag, Singapore Graph Neural Networks: Foundations, Frontiers, and Applications
Book SynopsisDeep Learning models are at the core of artificial intelligence research today. It is well known that deep learning techniques are disruptive for Euclidean data, such as images or sequence data, and not immediately applicable to graph-structured data such as text. This gap has driven a wave of research for deep learning on graphs, including graph representation learning, graph generation, and graph classification. The new neural network architectures on graph-structured data (graph neural networks, GNNs in short) have performed remarkably on these tasks, demonstrated by applications in social networks, bioinformatics, and medical informatics. Despite these successes, GNNs still face many challenges ranging from the foundational methodologies to the theoretical understandings of the power of the graph representation learning.This book provides a comprehensive introduction of GNNs. It first discusses the goals of graph representation learning and then reviews the history, current developments, and future directions of GNNs. The second part presents and reviews fundamental methods and theories concerning GNNs while the third part describes various frontiers that are built on the GNNs. The book concludes with an overview of recent developments in a number of applications using GNNs. This book is suitable for a wide audience including undergraduate and graduate students, postdoctoral researchers, professors and lecturers, as well as industrial and government practitioners who are new to this area or who already have some basic background but want to learn more about advanced and promising techniques and applications.Table of ContentsChapter 1. Representation Learning.- Chapter 2. Graph Representation Learning.- Chapter 3. Graph Neural Networks.- Chapter 4. Graph Neural Networks for Node Classification.- Chapter 5. The Expressive Power of Graph Neural Networks.- Chapter 6. Graph Neural Networks: Scalability.- Chapter 7. Interpretability in Graph Neural Networks.- Chapter 8. "Graph Neural Networks: Adversarial Robustness".- Chapter 9. Graph Neural Networks: Graph Classification.- Chapter 10. Graph Neural Networks: Link Prediction.- Chapter 11. Graph Neural Networks: Graph Generation.- Chapter 12. Graph Neural Networks: Graph Transformation.- Chapter 13. Graph Neural Networks: Graph Matching.- Chapter 14. "Graph Neural Networks: Graph Structure Learning". Chapter 15. Dynamic Graph Neural Networks.- Chapter 16. Heterogeneous Graph Neural Networks.- Chapter 17. Graph Neural Network: AutoML.- Chapter 18. Graph Neural Networks: Self-supervised Learning.- Chapter 19. Graph Neural Network in Modern Recommender Systems.- Chapter 20. Graph Neural Network in Computer Vision.- Chapter 21. Graph Neural Networks in Natural Language Processing.- Chapter 22. Graph Neural Networks in Program Analysis.- Chapter 23. Graph Neural Networks in Software Mining.- Chapter 24. "GNN-based Biomedical Knowledge Graph Mining in Drug Development".- Chapter 25. "Graph Neural Networks in Predicting Protein Function and Interactions".- Chapter 26. Graph Neural Networks in Anomaly Detection.- Chapter 27. Graph Neural Networks in Urban Intelligence.
£85.49
Springer Verlag, Singapore Graph Neural Networks: Foundations, Frontiers, and Applications
Book SynopsisDeep Learning models are at the core of artificial intelligence research today. It is well known that deep learning techniques are disruptive for Euclidean data, such as images or sequence data, and not immediately applicable to graph-structured data such as text. This gap has driven a wave of research for deep learning on graphs, including graph representation learning, graph generation, and graph classification. The new neural network architectures on graph-structured data (graph neural networks, GNNs in short) have performed remarkably on these tasks, demonstrated by applications in social networks, bioinformatics, and medical informatics. Despite these successes, GNNs still face many challenges ranging from the foundational methodologies to the theoretical understandings of the power of the graph representation learning.This book provides a comprehensive introduction of GNNs. It first discusses the goals of graph representation learning and then reviews the history, current developments, and future directions of GNNs. The second part presents and reviews fundamental methods and theories concerning GNNs while the third part describes various frontiers that are built on the GNNs. The book concludes with an overview of recent developments in a number of applications using GNNs. This book is suitable for a wide audience including undergraduate and graduate students, postdoctoral researchers, professors and lecturers, as well as industrial and government practitioners who are new to this area or who already have some basic background but want to learn more about advanced and promising techniques and applications.Table of ContentsChapter 1. Representation Learning.- Chapter 2. Graph Representation Learning.- Chapter 3. Graph Neural Networks.- Chapter 4. Graph Neural Networks for Node Classification.- Chapter 5. The Expressive Power of Graph Neural Networks.- Chapter 6. Graph Neural Networks: Scalability.- Chapter 7. Interpretability in Graph Neural Networks.- Chapter 8. "Graph Neural Networks: Adversarial Robustness".- Chapter 9. Graph Neural Networks: Graph Classification.- Chapter 10. Graph Neural Networks: Link Prediction.- Chapter 11. Graph Neural Networks: Graph Generation.- Chapter 12. Graph Neural Networks: Graph Transformation.- Chapter 13. Graph Neural Networks: Graph Matching.- Chapter 14. "Graph Neural Networks: Graph Structure Learning". Chapter 15. Dynamic Graph Neural Networks.- Chapter 16. Heterogeneous Graph Neural Networks.- Chapter 17. Graph Neural Network: AutoML.- Chapter 18. Graph Neural Networks: Self-supervised Learning.- Chapter 19. Graph Neural Network in Modern Recommender Systems.- Chapter 20. Graph Neural Network in Computer Vision.- Chapter 21. Graph Neural Networks in Natural Language Processing.- Chapter 22. Graph Neural Networks in Program Analysis.- Chapter 23. Graph Neural Networks in Software Mining.- Chapter 24. "GNN-based Biomedical Knowledge Graph Mining in Drug Development".- Chapter 25. "Graph Neural Networks in Predicting Protein Function and Interactions".- Chapter 26. Graph Neural Networks in Anomaly Detection.- Chapter 27. Graph Neural Networks in Urban Intelligence.
£56.99
Springer Verlag, Singapore Image and Graphics Technologies and Applications:
Book SynopsisThis book constitutes the refereed proceedings of the 16th Conference on Image and Graphics Technologies and Applications, IGTA 2021, held in Beijing, China in June, 2021. The 21 papers presented were carefully reviewed and selected from 86 submissions. They provide a forum for sharing progresses in the areas of image processing technology; image analysis and understanding; computer vision and pattern recognition; big data mining, computer graphics and VR, as well as image technology applications. The volume contains the following thematic blocks: image processing and enhancement techniques (image information acquisition, image/video coding, image/video transmission, image/video storage, compression, completion, dehazing, reconstruction and display, etc.); biometric identification techniques (biometric identification and authentication techniques including face, fingerprint, iris and palm-print, etc.); machine vision and 3D reconstruction (visual information acquisition, camera calibration, stereo vision, 3D reconstruction, and applications of machine vision in industrial inspection, etc.); image/video big data analysis and understanding (object detection and recognition, image/video retrieval, image segmentation, matching, analysis and understanding); computer graphics (modeling, rendering, algorithm simplification and acceleration techniques, realistic scene generation, 3D reconstruction algorithm, system and application, etc.); virtual reality and human-computer interaction (virtual scene generation techniques, tracing and positioning techniques for large-scale space, augmented reality techniques, human-computer interaction techniques based on computer vision, etc.); applications of image and graphics (image/video processing and transmission, biomedical engineering applications, information security, digital watermarking, text processing and transmission, remote sensing, telemetering, etc.); other research works and surveys related to the applications of image and graphics technology.Table of ContentsImage processing and enhancement techniques.- Biometric identification techniques.- Machine vision and 3D reconstruction.- Image/Video big data analysis and understanding.- Computer graphics.- Virtual reality and human-computer interaction.- Applications of image and graphics.
£58.49
Springer Verlag, Singapore Machine Learning: The Basics
Book SynopsisMachine learning (ML) has become a commonplace element in our everyday lives and a standard tool for many fields of science and engineering. To make optimal use of ML, it is essential to understand its underlying principles. This book approaches ML as the computational implementation of the scientific principle. This principle consists of continuously adapting a model of a given data-generating phenomenon by minimizing some form of loss incurred by its predictions. The book trains readers to break down various ML applications and methods in terms of data, model, and loss, thus helping them to choose from the vast range of ready-made ML methods.The book’s three-component approach to ML provides uniform coverage of a wide range of concepts and techniques. As a case in point, techniques for regularization, privacy-preservation as well as explainability amount to specific design choices for the model, data, and loss of a ML method. Table of ContentsIntroduction.- Components of ML.- The Landscape of ML.- Empirical Risk Minimization.- Gradient-Based Learning.- Model Validation and Selection.- Regularization.- Clustering.- Feature Learning.- Transparant and Explainable ML.
£44.72
Springer Verlag, Singapore Computational Intelligence in Machine Learning:
Book SynopsisThe book includes select proceedings of the International Conference on Computational Intelligence in Machine Learning (ICCIML 2021). The book constitutes peer-reviewed papers on machine learning, computational intelligence, the internet of things, and smart city applications emphasizing multi-disciplinary research in artificial intelligence and cyber-physical systems. This book addresses the comprehensive nature of computational intelligence, artificial intelligence, machine learning, and deep learning to emphasize its character in modeling, identification, optimization, prediction, forecasting, and control of future intelligent systems. The book will be useful for researchers, research scholars, and students to formulate their research ideas and find future directions in these areas. It will help the readers to solve a diverse range of problems in industries and their real-world applications.Table of ContentsMachine Learning-based Project Resource Allocation Fitment Analysis System – (ML-PRAFS).- Electric Theft Detection using Un-supervised Machine Learning Based Matrix Profile and K Means Clustering Technique.- Placement Analysis – A New Approach to Ease the Recruitment Process.- Continuous Assessment Analyzer using Django.- Fuzzy Logic in Battery Energy Storage System (Bess).- Fault Classification of Cooling Fans using a CNN-based Approach.- Violence Recognition using Convolutional Neural Networks.- Automated Grading of Citrus Suhuiensis Fruit using Deep Learning Method.- The Future of Car Automation Field with Smart Driverless Technologies.- Diagnosis and Medicine Prediction for Covid-19 using Machine Learning Approach.- Automated Guided Vehicle Robot Localization with Sensor Fusion.- Implementation of Industrial Automation Water Distribution System Utilizing PLC: A Laboratory Set-up.- Control of Thin McKibben Muscles in an Antagonistic Pair Configuration.- Defect Severity Classification of Complex Composites using CWT and CNN.- Detection of Mobile Phone Usage While Driving using Computer Vision and Deep Learning.- Industry Revolution 4.0 Knowledge Assessment in Malaysia.
£332.49
Springer Verlag, Singapore Computational Intelligence in Machine Learning:
Book SynopsisThe book includes select proceedings of the International Conference on Computational Intelligence in Machine Learning (ICCIML 2021). The book constitutes peer-reviewed papers on machine learning, computational intelligence, the internet of things, and smart city applications emphasizing multi-disciplinary research in artificial intelligence and cyber-physical systems. This book addresses the comprehensive nature of computational intelligence, artificial intelligence, machine learning, and deep learning to emphasize its character in modeling, identification, optimization, prediction, forecasting, and control of future intelligent systems. The book will be useful for researchers, research scholars, and students to formulate their research ideas and find future directions in these areas. It will help the readers to solve a diverse range of problems in industries and their real-world applications.Table of ContentsMachine Learning-based Project Resource Allocation Fitment Analysis System – (ML-PRAFS).- Electric Theft Detection using Un-supervised Machine Learning Based Matrix Profile and K Means Clustering Technique.- Placement Analysis – A New Approach to Ease the Recruitment Process.- Continuous Assessment Analyzer using Django.- Fuzzy Logic in Battery Energy Storage System (Bess).- Fault Classification of Cooling Fans using a CNN-based Approach.- Violence Recognition using Convolutional Neural Networks.- Automated Grading of Citrus Suhuiensis Fruit using Deep Learning Method.- The Future of Car Automation Field with Smart Driverless Technologies.- Diagnosis and Medicine Prediction for Covid-19 using Machine Learning Approach.- Automated Guided Vehicle Robot Localization with Sensor Fusion.- Implementation of Industrial Automation Water Distribution System Utilizing PLC: A Laboratory Set-up.- Control of Thin McKibben Muscles in an Antagonistic Pair Configuration.- Defect Severity Classification of Complex Composites using CWT and CNN.- Detection of Mobile Phone Usage While Driving using Computer Vision and Deep Learning.- Industry Revolution 4.0 Knowledge Assessment in Malaysia.
£297.49
Springer Verlag, Singapore Artificial Intelligence with Python
Book SynopsisEntering the field of artificial intelligence and data science can seem daunting to beginners with little to no prior background, especially those with no programming experience. The concepts used in self-driving cars and virtual assistants like Amazon’s Alexa may seem very complex and difficult to grasp. The aim of Artificial Intelligence in Python is to make AI accessible and easy to understand for people with little to no programming experience though practical exercises. Newcomers will gain the necessary knowledge on how to create such systems, which are capable of executing tasks that require some form of human-like intelligence. This book introduces readers to various topics and examples of programming in Python, as well as key concepts in artificial intelligence. Python programming skills will be imparted as we go along. Concepts and code snippets will be covered in a step-by-step manner, to guide and instill confidence in beginners. Complex subjects in deep learning and machine learning will be broken down into easy-to-digest content and examples. Artificial intelligence implementations will also be shared, allowing beginners to generate their own artificial intelligence algorithms for reinforcement learning, style transfer, chatbots, speech, and natural language processing.Table of ContentsPart I Python.- 1 About Python.- 2 What’s Python?.- 3 An Introductory Example.- 4 Basic Python.- 5 Intermediate Python.- 6 Advanced Python.- 7 Python for data analysis.- Part II Artificial Intelligence Basics.- 8 Introduction to artificial intelligence.- 9 Data wrangling.- 10 Regression.- 11 Classification.- 12 Clustering.- 13 Association Rules.- Part III Artificial Intelligence.- Implementations.- 14 Text Mining.- 15 Image Processing.- 16 Convolutional Neural Networks.- 17 Chatbot, Speech and NLP.- 18 Deep Convolutional Generative Adversarial Network.- 19 Neural style transfer.- 20 Reinforcement learning.- 21 References.
£45.55
Springer Verlag, Singapore Advances in Machine Learning for Big Data
Book SynopsisThis book focuses on research aspects of ensemble approaches of machine learning techniques that can be applied to address the big data problems. In this book, various advancements of machine learning algorithms to extract data-driven decisions from big data in diverse domains such as the banking sector, healthcare, social media, and video surveillance are presented in several chapters. Each of them has separate functionalities, which can be leveraged to solve a specific set of big data applications. This book is a potential resource for various advances in the field of machine learning and data science to solve big data problems with many objectives. It has been observed from the literature that several works have been focused on the advancement of machine learning in various fields like biomedical, stock prediction, sentiment analysis, etc. However, limited discussions have been carried out on application of advanced machine learning techniques in solving big data problems. Table of ContentsDeep Learning for Supervised Learning.- Deep Learning for Unsupervised Learning.- Support Vector Machine for Regression.- Support Vector Machine for Classification.- Decision Tree for Regression.- Higher Order Neural Networks.- Competitive Learning.- Semi-supervised Learning.- Multi-objective Optimization Techniques.- Techniques for Feature Selection/Extraction.- Techniques for Task Relevant Big Data Analysis.- Techniques for Post Processing Task in Big Data Analysis.- Customer Relationship Management.
£125.99
Springer Verlag, Singapore Privacy-Preserving Machine Learning
Book SynopsisThis book provides a thorough overview of the evolution of privacy-preserving machine learning schemes over the last ten years, after discussing the importance of privacy-preserving techniques. In response to the diversity of Internet services, data services based on machine learning are now available for various applications, including risk assessment and image recognition. In light of open access to datasets and not fully trusted environments, machine learning-based applications face enormous security and privacy risks. In turn, it presents studies conducted to address privacy issues and a series of proposed solutions for ensuring privacy protection in machine learning tasks involving multiple parties. In closing, the book reviews state-of-the-art privacy-preserving techniques and examines the security threats they face.Table of ContentsIntroduction.- Secure Cooperative Learning in Early Years.- Outsourced Computation for Learning.- Secure Distributed Learning.- Learning with Differential Privacy.- Applications - Privacy-Preserving Image Processing.- Threats in Open Environment.- Conclusion.
£42.74
Springer Verlag, Singapore Marketing and Smart Technologies: Proceedings of
Book SynopsisThis book includes selected papers presented at the International Conference on Marketing and Technologies (ICMarkTech 2021), held at University of La Laguna, Tenerife, Spain, during December 2–4, 2021. It covers up-to-date cutting-edge research on artificial intelligence applied in marketing, virtual and augmented reality in marketing, business intelligence databases and marketing, data mining and big data, marketing data science, web marketing, e-commerce and v-commerce, social media and networking, geomarketing and IoT, marketing automation and inbound marketing, machine learning applied to marketing, customer data management and CRM, and neuromarketing technologies.
£199.99
Springer Verlag, Singapore Artificial Intelligence with Python
Book SynopsisEntering the field of artificial intelligence and data science can seem daunting to beginners with little to no prior background, especially those with no programming experience. The concepts used in self-driving cars and virtual assistants like Amazon’s Alexa may seem very complex and difficult to grasp. The aim of Artificial Intelligence in Python is to make AI accessible and easy to understand for people with little to no programming experience though practical exercises. Newcomers will gain the necessary knowledge on how to create such systems, which are capable of executing tasks that require some form of human-like intelligence. This book introduces readers to various topics and examples of programming in Python, as well as key concepts in artificial intelligence. Python programming skills will be imparted as we go along. Concepts and code snippets will be covered in a step-by-step manner, to guide and instill confidence in beginners. Complex subjects in deep learning and machine learning will be broken down into easy-to-digest content and examples. Artificial intelligence implementations will also be shared, allowing beginners to generate their own artificial intelligence algorithms for reinforcement learning, style transfer, chatbots, speech, and natural language processing.Table of ContentsPart I Python.- 1 About Python.- 2 What’s Python?.- 3 An Introductory Example.- 4 Basic Python.- 5 Intermediate Python.- 6 Advanced Python.- 7 Python for data analysis.- Part II Artificial Intelligence Basics.- 8 Introduction to artificial intelligence.- 9 Data wrangling.- 10 Regression.- 11 Classification.- 12 Clustering.- 13 Association Rules.- Part III Artificial Intelligence.- Implementations.- 14 Text Mining.- 15 Image Processing.- 16 Convolutional Neural Networks.- 17 Chatbot, Speech and NLP.- 18 Deep Convolutional Generative Adversarial Network.- 19 Neural style transfer.- 20 Reinforcement learning.- 21 References.
£37.85
Springer Verlag, Singapore Computer Vision and Machine Learning in
Book SynopsisThis book is as an extension of previous book “Computer Vision and Machine Learning in Agriculture” for academicians, researchers, and professionals interested in solving the problems of agricultural plants and products for boosting production by rendering the advanced machine learning including deep learning tools and techniques to computer vision algorithms. The book contains 15 chapters. The first three chapters are devoted to crops harvesting, weed, and multi-class crops detection with the help of robots and UAVs through machine learning and deep learning algorithms for smart agriculture. Next, two chapters describe agricultural data retrievals and data collections. Chapters 6, 7, 8 and 9 focuses on yield estimation, crop maturity detection, agri-food product quality assessment, and medicinal plant recognition, respectively. The remaining six chapters concentrates on optimized disease recognition through computer vision-based machine and deep learning strategies.Table of ContentsHarvesting robots for smart agriculture.- Drone-based weed detection architectures using deep learning algorithms and real-time analytics.- A deep learning-based detection system of multi-class crops and orchards using a UAV.- Real-life agricultural data retrieval for large scale annotation flow optimization.- Design and analysis of IoT-based modern agriculture monitoring system for real time data collection.- Estimation of wheat yield based on precipitation and evapotranspiration using soft computing methods.- Coconut maturity recognition using convolutional neural network.- Agri food products quality assessment methods.- Medicinal plant recognition from leaf images using deep learning.- ESMO based plant leaf disease identification: A machine learning approach.- Deep learning-based cuali flower disease classification.- An Intelligent System for Crop Disease Identification and Dispersion Forecasting in SriLanka.- Apple leaves diseases detection using deep convolutional neural networks and transfer learning.- A deep learning paradigm for detection and segmentation of plant leaves diseases.- Early-stage prediction of plant leaf diseases using deep learning models.
£125.99
Springer Verlag, Singapore Deep Reinforcement Learning
Book SynopsisDeep reinforcement learning has attracted considerable attention recently. Impressive results have been achieved in such diverse fields as autonomous driving, game playing, molecular recombination, and robotics. In all these fields, computer programs have taught themselves to understand problems that were previously considered to be very difficult. In the game of Go, the program AlphaGo has even learned to outmatch three of the world’s leading players.Deep reinforcement learning takes its inspiration from the fields of biology and psychology. Biology has inspired the creation of artificial neural networks and deep learning, while psychology studies how animals and humans learn, and how subjects’ desired behavior can be reinforced with positive and negative stimuli. When we see how reinforcement learning teaches a simulated robot to walk, we are reminded of how children learn, through playful exploration. Techniques that are inspired by biology and psychology work amazingly well in computers: animal behavior and the structure of the brain as new blueprints for science and engineering. In fact, computers truly seem to possess aspects of human behavior; as such, this field goes to the heart of the dream of artificial intelligence. These research advances have not gone unnoticed by educators. Many universities have begun offering courses on the subject of deep reinforcement learning. The aim of this book is to provide an overview of the field, at the proper level of detail for a graduate course in artificial intelligence. It covers the complete field, from the basic algorithms of Deep Q-learning, to advanced topics such as multi-agent reinforcement learning and meta learning.Table of ContentsContents1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11.1 What is Deep Reinforcement Learning? . . . . . . . . . . . . . . . . . . . . . . . . 11.2 Three Machine Learning Paradigms . . . . . . . . . . . . . . . . . . . . . . . . . . . . 121.3 Overview of the Book . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 172 Tabular Value-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 232.1 Sequential Decision Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 252.2 Tabular Value-Based Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 272.3 Classic Gym Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 552.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 572.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 603 Approximating the Value Function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 633.1 Large, High-Dimensional, Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . 663.2 Deep Value-Based Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 693.3 Atari 2600 Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 833.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 863.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 874 Policy-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 894.1 Continuous Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 914.2 Policy-Based Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 944.3 Locomotion and Visuo-Motor Environments . . . . . . . . . . . . . . . . . . . . 1114.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1154.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1165 Model-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1195.1 Dynamics Models of High-Dimensional Problems . . . . . . . . . . . . . . . 1225.2 Learning and Planning Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1235.3 High-dimensional Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1365.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 142viiviii CONTENTS5.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1446 Two-Agent Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1476.1 Two-Agent Zero-Sum Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1506.2 Tabula Rasa Self-Play Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1566.3 Self-Play Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1786.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1866.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1887 Multi-Agent Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1917.1 Multi-Agent Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1937.2 Multi-Agent Reinforcement Learning Agents . . . . . . . . . . . . . . . . . . . . 2027.3 Multi-Agent Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2147.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2217.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2238 Hierarchical Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 2258.1 Granularity of the Structure of Problems . . . . . . . . . . . . . . . . . . . . . . . 2278.2 Divide and Conquer for Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2298.3 Hierarchical Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2358.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2408.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2419 Meta Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2439.1 Learning to Learn Related Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2469.2 Transfer Learning and Meta Learning Agents . . . . . . . . . . . . . . . . . . . 2479.3 Meta-Learning Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2619.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2679.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26810 Further Developments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27110.1 Developments in Deep Reinforcement Learning . . . . . . . . . . . . . . . . . 27110.2 Main Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27410.3 The Future of Articial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . . 279A Deep Reinforcement Learning Suites . . . . . . . . . . . . . . . . . . . . . . . . . . . . 283A.1 Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 284A.2 Agent Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 285A.3 Deep Learning Suites . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 286B Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 287B.1 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 287B.2 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 294B.3 Datasets and Software . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 311CONTENTS ixC Mathematical Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 323C.1 Sets and Functions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 323C.2 Probability Distributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 326C.3 Derivative of an Expectation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 334C.4 Bellman Equations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 335References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 337Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 379Index . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 381x CONTENTSContents1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11.1 What is Deep Reinforcement Learning? . . . . . . . . . . . . . . . . . . . . . . . . 11.1.1 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21.1.2 Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31.1.3 Deep Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . 31.1.4 Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41.1.5 Four Related Fields . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61.1.5.1 Psychology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81.1.5.2 Mathematics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81.1.5.3 Engineering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 101.1.5.4 Biology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111.2 Three Machine Learning Paradigms . . . . . . . . . . . . . . . . . . . . . . . . . . . . 121.2.1 Supervised Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 141.2.2 Unsupervised Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 151.2.3 Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 161.3 Overview of the Book . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 171.3.1 Prerequisite Knowledge . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 181.3.2 Structure of the Book . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 192 Tabular Value-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 232.1 Sequential Decision Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 252.2 Tabular Value-Based Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 272.2.1 Agent and Environment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 272.2.2 Markov Decision Process . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 282.2.2.1 State ( . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 292.2.2.2 Action . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 302.2.2.3 Transition )0 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 312.2.2.4 Reward '0 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 332.2.2.5 Discount Factor W . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 332.2.2.6 Policy Function c . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 332.2.3 MDP Objective . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34xixii Contents2.2.3.1 Trace g . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 352.2.3.2 State Value + . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 362.2.3.3 State-Action Value & . . . . . . . . . . . . . . . . . . . . . . . . . . 372.2.3.4 Reinforcement Learning Objective . . . . . . . . . . . . . . 382.2.3.5 Bellman Equation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 392.2.4 MDP Solution Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 392.2.4.1 Hands On: Value Iteration in Gym . . . . . . . . . . . . . . . 412.2.4.2 Model-Free Learning . . . . . . . . . . . . . . . . . . . . . . . . . . 442.2.4.3 Exploration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 472.2.4.4 O-Policy Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 492.2.4.5 Hands On: Q-learning on Taxi . . . . . . . . . . . . . . . . . . 522.3 Classic Gym Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 552.3.1 Mountain Car and Cartpole . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 552.3.2 Path Planning and Board Games . . . . . . . . . . . . . . . . . . . . . . . . 562.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 572.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 603 Approximating the Value Function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 633.1 Large, High-Dimensional, Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . 663.1.1 Atari Arcade Games . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 673.1.2 Real-Time Strategy and Video Games . . . . . . . . . . . . . . . . . . . . 683.2 Deep Value-Based Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 693.2.1 Generalization of Large Problem with Deep Learning . . . . . 693.2.1.1 Minimizing Supervised Target Loss . . . . . . . . . . . . . 693.2.1.2 Bootstrapping Q-Values . . . . . . . . . . . . . . . . . . . . . . . 703.2.1.3 Deep Reinforcement Learning Target-Error . . . . . 713.2.2 Three Problems: Coverage, Correlation, Convergence . . . . . 723.2.2.1 Coverage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 723.2.2.2 Correlation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 723.2.2.3 Convergence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 733.2.3 Stable Deep Value-Based Learning . . . . . . . . . . . . . . . . . . . . . . 743.2.3.1 Decorrelating States . . . . . . . . . . . . . . . . . . . . . . . . . . . 753.2.3.2 Infrequent Updates of Target Weights . . . . . . . . . . . 763.2.3.3 Hands On: DQN and Breakout Gym Example . . . . . 763.2.4 Improving Exploration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 803.2.4.1 Overestimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 813.2.4.2 Distributional Methods . . . . . . . . . . . . . . . . . . . . . . . . 833.3 Atari 2600 Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 833.3.1 Network Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 843.3.2 Benchmarking Atari . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 853.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 863.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 87Contents xiii4 Policy-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 894.1 Continuous Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 914.1.1 Continuous Policies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 914.1.2 Stochastic Policies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 914.1.3 Environments: Gym and MuJoCo . . . . . . . . . . . . . . . . . . . . . . . 924.1.3.1 Robotics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 924.1.3.2 Physics Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 924.1.3.3 Games . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 944.2 Policy-Based Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 944.2.1 Policy-Based Algorithm: REINFORCE . . . . . . . . . . . . . . . . . . . 954.2.2 Bias-Variance trade-o in Policy-Based Methods . . . . . . . . . 984.2.3 Actor Critic Bootstrapping . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 994.2.4 Baseline Subtraction with Advantage Function . . . . . . . . . . . 1014.2.5 Trust Region Optimization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1044.2.6 Entropy and Exploration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1064.2.7 Deterministic Policy Gradient . . . . . . . . . . . . . . . . . . . . . . . . . . 1074.2.8 Hands On: PPO and DDPG MuJoCo Examples . . . . . . . . . . . . . 1104.3 Locomotion and Visuo-Motor Environments . . . . . . . . . . . . . . . . . . . . 1114.3.1 Locomotion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1114.3.2 Visuo-Motor Interaction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1134.3.3 Benchmarking . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1144.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1154.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1165 Model-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1195.1 Dynamics Models of High-Dimensional Problems . . . . . . . . . . . . . . . 1225.2 Learning and Planning Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1235.2.1 Learning the Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1285.2.1.1 Modeling Uncertainty . . . . . . . . . . . . . . . . . . . . . . . . . 1285.2.1.2 Latent Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1295.2.2 Planning with the Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1315.2.2.1 Trajectory Rollouts and Model-Predictive Control 1325.2.2.2 End-to-end Learning and Planning-by-Network . 1335.3 High-dimensional Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1365.3.1 Overview of Model-Based Experiments . . . . . . . . . . . . . . . . . . 1375.3.2 Small Navigation Tasks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1385.3.3 Robotic Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1395.3.4 Games Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1395.3.5 Hands On: PlaNet Example . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1415.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1425.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 144xiv Contents6 Two-Agent Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1476.1 Two-Agent Zero-Sum Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1506.1.1 The Diculty of Playing Go . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1526.1.2 AlphaGo Achievements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1556.2 Tabula Rasa Self-Play Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1566.2.1 Move-Level Self Play . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1606.2.1.1 Minimax . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1616.2.1.2 Monte Carlo Tree Search . . . . . . . . . . . . . . . . . . . . . . 1646.2.2 Example-Level Self Play . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1716.2.2.1 Policy and Value Network . . . . . . . . . . . . . . . . . . . . . 1726.2.2.2 Stability and Exploration . . . . . . . . . . . . . . . . . . . . . . 1726.2.3 Tournament-Level Self Play . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1746.2.3.1 Self-Play Curriculum Learning . . . . . . . . . . . . . . . . . 1756.2.3.2 Supervised Curriculum Learning . . . . . . . . . . . . . . . 1756.3 Self-Play Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1786.3.1 How to Design a World Class Go Program? . . . . . . . . . . . . . . 1786.3.2 AlphaGo Zero Performance . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1806.3.3 AlphaZero . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1816.3.4 Open Self-Play Frameworks . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1836.3.5 Hands On: Hex in Polygames Example . . . . . . . . . . . . . . . . . . . . 1846.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1866.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1887 Multi-Agent Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1917.1 Multi-Agent Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1937.1.1 Competitive Behavior . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1967.1.2 Cooperative Behavior . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1977.1.3 Mixed Behavior . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1987.1.4 Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2007.1.4.1 Partial Observability . . . . . . . . . . . . . . . . . . . . . . . . . . 2017.1.4.2 Nonstationary Environments . . . . . . . . . . . . . . . . . . 2017.1.4.3 Large State Space . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2027.2 Multi-Agent Reinforcement Learning Agents . . . . . . . . . . . . . . . . . . . . 2027.2.1 Competitive Behavior . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2037.2.1.1 Counterfactual Regret Minimization . . . . . . . . . . . . 2037.2.1.2 Deep Counterfactual Regret Minimization . . . . . . . 2047.2.2 Cooperative Behavior . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2067.2.2.1 Centralized Training/Decentralized Execution . . . 2067.2.2.2 Opponent Modeling . . . . . . . . . . . . . . . . . . . . . . . . . . . 2077.2.2.3 Communication . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2087.2.2.4 Psychology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2087.2.3 Mixed Behavior . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2097.2.3.1 Evolutionary Algorithms . . . . . . . . . . . . . . . . . . . . . . 2097.2.3.2 Swarm Computing . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2117.2.3.3 Population-Based Training . . . . . . . . . . . . . . . . . . . . . 212Contents xv7.2.3.4 Self-Play Leagues . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2137.3 Multi-Agent Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2147.3.1 Competitive Behavior: Poker . . . . . . . . . . . . . . . . . . . . . . . . . . . 2147.3.2 Cooperative Behavior: Hide and Seek. . . . . . . . . . . . . . . . . . . . 2167.3.3 Mixed Behavior: Capture the Flag and StarCraft . . . . . . . . . . 2187.3.4 Hands On: Hide and Seek in the Gym Example . . . . . . . . . . . . 2207.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2217.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2238 Hierarchical Reinforcement Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 2258.1 Granularity of the Structure of Problems . . . . . . . . . . . . . . . . . . . . . . . 2278.1.1 Advantages . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2278.1.2 Disadvantages . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2288.2 Divide and Conquer for Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2298.2.1 The Options Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2298.2.2 Finding Subgoals . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2318.2.3 Overview of Hierarchical Algorithms . . . . . . . . . . . . . . . . . . . . 2318.2.3.1 Tabular . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2328.2.3.2 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2328.3 Hierarchical Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2358.3.1 Four Rooms and Robot Tasks . . . . . . . . . . . . . . . . . . . . . . . . . . . 2358.3.2 Montezuma’s Revenge . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2368.3.3 Multi-Agent Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2388.3.4 Hands On: Hierarchical Actor Citic Example . . . . . . . . . . . . . . 2388.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2408.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2419 Meta Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2439.1 Learning to Learn Related Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2469.2 Transfer Learning and Meta Learning Agents . . . . . . . . . . . . . . . . . . . 2479.2.1 Transfer Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2489.2.1.1 Task Similarity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2489.2.1.2 Pretraining and Finetuning . . . . . . . . . . . . . . . . . . . . 2499.2.1.3 Hands-on: Pretraining Example . . . . . . . . . . . . . . . . . 2499.2.1.4 Multi-task learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2509.2.1.5 Domain Adaptation . . . . . . . . . . . . . . . . . . . . . . . . . . . 2519.2.2 Meta Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2539.2.2.1 Evaluating Few-Shot Learning Problems . . . . . . . . 2539.2.2.2 Deep Meta Learning Algorithms . . . . . . . . . . . . . . . 2549.2.2.3 Recurrent Meta Learning . . . . . . . . . . . . . . . . . . . . . . 2569.2.2.4 Model-Agnostic Meta Learning . . . . . . . . . . . . . . . . . 2579.2.2.5 Hyperparameter Optimization . . . . . . . . . . . . . . . . . 2599.2.2.6 Meta Learning and Curriculum Learning . . . . . . . . 2609.2.2.7 From Few-Shot to Zero-Shot Learning . . . . . . . . . . 2609.3 Meta-Learning Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 261xvi Contents9.3.1 Image Processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2629.3.2 Natural Language Processing . . . . . . . . . . . . . . . . . . . . . . . . . . . 2639.3.3 Meta Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2639.3.4 Meta World . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2649.3.5 Alchemy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2659.3.6 Hands-on: Meta World Example . . . . . . . . . . . . . . . . . . . . . . . . . 2669.4 Summary and Further Reading . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2679.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26810 Further Developments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27110.1 Developments in Deep Reinforcement Learning . . . . . . . . . . . . . . . . . 27110.1.1 Tabular and Single-Agent Methods . . . . . . . . . . . . . . . . . . . . . . 27210.1.2 Deep Learning Model-Free Methods . . . . . . . . . . . . . . . . . . . . . 27210.1.3 Multi-Agent and Imperfect Information . . . . . . . . . . . . . . . . . . 27210.1.4 A Framework for Learning by Doing . . . . . . . . . . . . . . . . . . . . 27310.2 Main Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27410.2.1 Latent Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27510.2.2 Self Play . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27510.2.3 Hierarchical Reinforcement Learning . . . . . . . . . . . . . . . . . . . . 27510.2.4 Transfer Learning and Meta Learning . . . . . . . . . . . . . . . . . . . 27610.2.5 Population-Based Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27610.2.6 Exploration and Intrinsic Motivation . . . . . . . . . . . . . . . . . . . . 27710.2.7 Explainable AI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27810.2.8 Generalization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27810.3 The Future of Articial Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . . 279A Deep Reinforcement Learning Suites . . . . . . . . . . . . . . . . . . . . . . . . . . . . 283A.1 Environments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 284A.2 Agent Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 285A.3 Deep Learning Suites . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 286B Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 287B.1 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 287B.1.1 Training Set and Test Set . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 288B.1.2 Curse of Dimensionality . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 289B.1.3 Overtting and the Bias-Variance Trade-O . . . . . . . . . . . . . . 290B.2 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 294B.2.1 Weights, Neurons . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 294B.2.2 Backpropagation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 295B.2.3 End-to-end Feature Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 297B.2.4 Convolutional Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 300B.2.5 Recurrent Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 303B.2.6 More Network Architectures . . . . . . . . . . . . . . . . . . . . . . . . . . . 305B.2.7 Overtting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 310B.3 Datasets and Software . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 311Contents xviiB.3.1 Keras, TensorFlow, PyTorch . . . . . . . . . . . . . . . . . . . . . . . . . . . . 312B.3.2 MNIST and ImageNet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 313B.3.3 GPU Implementations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 315B.3.4 Hands On: Classication Example . . . . . . . . . . . . . . . . . . . . . . . . 316B.3.5 Exercises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 319C Mathematical Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 323C.1 Sets and Functions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 323C.1.1 Sets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 323C.1.2 Functions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 325C.2 Probability Distributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 326C.2.1 Discrete Probability Distributions . . . . . . . . . . . . . . . . . . . . . . . 326C.2.2 Continuous Probability Distributions . . . . . . . . . . . . . . . . . . . . 327C.2.3 Conditional Distributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 329C.2.4 Expectation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 330C.2.4.1 Expectation of a Random Variable . . . . . . . . . . . . . . 330C.2.4.2 Expectation of a Function of a Random Variable . 331C.2.5 Information Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 332C.2.5.1 Information . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 332C.2.5.2 Entropy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 332C.2.5.3 Cross-entropy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 333C.2.5.4 Kullback-Leibler Divergence . . . . . . . . . . . . . . . . . . . 333C.3 Derivative of an Expectation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 334C.4 Bellman Equations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 335References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 337Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 379Index . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 381
£40.49
Springer Verlag, Singapore Internet of Things Based Smart Healthcare:
Book SynopsisThis book provides both the developers and the users with an awareness of the challenges and opportunities of advancements in healthcare paradigm with the application and availability of advanced hardware, software, tools, technique or algorithm development stemming the Internet of Things. The book helps readers to bridge the gap in their three understanding of three major domains and their interconnections: Hardware tested and software APP development for data collection, intelligent protocols for analysis and knowledge extraction. Medical expertise to interpret extracted knowledge towards disease prediction or diagnosis and support. Security experts to ensure data correctness for precise advice. The book provides state-of-the-art overviews by active researchers, technically elaborating healthcare architectures/frameworks, protocols, algorithms, methodologies followed by experimental results and evaluation. Future direction and scope will be precisely documented for interested readers.Table of ContentsPart 1 IoT based Smart Healthcare.- Chapter 1 Introduction.- Chapter 2 Architecture for Smart Healthcare: Cloud vs Edge.- Chapter 3 Main Challenges and Concerns of Health IoT Data.- Part 2 Context and Body Vitals Monitoring Systems.- Chapter 4 Human Activity Recognition Systems Based on Sensor Data using Machine Learning.- Chapter 5 Human Activity Recognition Systems Based on Audio-Video Data using Machine Learning and Deep learning.- Chapter 6 Review of Body Vitals Monitoring Systems for Disease Prediction.- Chapter 7 Review of Context Aware System Implementations.- Part 3 Social Sensing Applications for Public Health.- Chapter 8 Types of Social Sensing Data.- Chapter 9 Social Data Analysis Techniques and Applications.- Chapter 10 Challenges and Limitations of Social Data Analysis Approaches.- Part 4 Reliability, Security and Privacy of Health Data.- Chapter 11 Quality of Service vs Quality of Experience for Real-time Smart Healthcare.- Chapter 12 Security and Privacy Issues of Health Data.- Chapter 13 Review of Performance Metrics and Corrective Measures for Health Data Analysis.
£132.99
Springer Verlag, Singapore Privacy Preservation in IoT: Machine Learning
Book SynopsisThis book aims to sort out the clear logic of the development of machine learning-driven privacy preservation in IoTs, including the advantages and disadvantages, as well as the future directions in this under-explored domain. In big data era, an increasingly massive volume of data is generated and transmitted in Internet of Things (IoTs), which poses great threats to privacy protection. Motivated by this, an emerging research topic, machine learning-driven privacy preservation, is fast booming to address various and diverse demands of IoTs. However, there is no existing literature discussion on this topic in a systematically manner. The issues of existing privacy protection methods (differential privacy, clustering, anonymity, etc.) for IoTs, such as low data utility, high communication overload, and unbalanced trade-off, are identified to the necessity of machine learning-driven privacy preservation. Besides, the leading and emerging attacks pose further threats to privacy protection in this scenario. To mitigate the negative impact, machine learning-driven privacy preservation methods for IoTs are discussed in detail on both the advantages and flaws, which is followed by potentially promising research directions. Readers may trace timely contributions on machine learning-driven privacy preservation in IoTs. The advances cover different applications, such as cyber-physical systems, fog computing, and location-based services. This book will be of interest to forthcoming scientists, policymakers, researchers, and postgraduates. Table of Contents· Chapter 1: Introduction o Privacy research landscape o Machine learning driven privacy preservation overview o Contribution of this monograph o Outline of the monograph · Chapter 2: Current Methods of Privacy Protection in IoTs o Cryptography based methods o Differential privacy methods o Anonymity-based methods o Clustering-based methods · Chapter 3: Decentralized Privacy Protection of IoTs using Blockchain-Enabled Federated Learning o Overview o System Modelling o Decentralized Privacy Protocols o Blockchain-enabled Federated Learning · Chapter 4: Personalized Privacy Protection of IoTs using GAN-Enhanced Differential Privacy o Overview o System Modelling o Personalized Privacy o GAN-Enhanced Differential Privacy · Chapter 5: Hybrid Privacy Protection of IoT using Reinforcement Learning o Overview o System Modelling o Hybrid Privacy o Markov Decision Process and Reinforcement Learning · Chapter 6: Future Directions o Trade-off optimization o Privacy preservation of digital twin o Privacy-preserving federated learning o Federated generative adversarial nets · Chapter 7: Summary and Outlook
£42.74
Springer Verlag, Singapore Environmental Informatics: Challenges and
Book SynopsisThis interdisciplinary book incorporates various aspects of environment, ecology, and natural disaster management including cognitive informatics and computing. It fosters research innovation and discovery on basic science and information technology for addressing various environmental problems, while providing the right solutions in environment, ecology, and disaster management. This book is a unique resource for researchers and practitioners of energy informatics in various scientific, technological, engineering, and social fields to disseminate original research on the application of digital technology and information management theory and practice to facilitate the global transition toward sustainable and resilient energy systems. Cognitive informatics is also the need of the hour and deals with cutting-edge and multidisciplinary research area that tackles the fundamental problems shared by modern informatics, computation, software engineering, AI, cybernetics, cognitive science, neuropsychology, medical science, systems science, philosophy, linguistics, economics, management science, and life sciences, which this book also presents.Table of ContentsChapter 1: Perspectives of Environmental Informatics and Systems Analysis Chapter 2: Planning of energy, environmental and ecological management systems Chapter 3: Simulation, optimization and Environmental decision support Chapter 4: Environmental geomatics - GIS, RS and other spatial information technologies Chapter 5: Cloud Computing, Big Data, Machine Learning in Environmental & Disaster Management Chapter 6: Urbanization – Smart City Supported with Environmental and Energy Systems & Technologies Chapter 7: Climate Change, Environmental Monitoring using Emerging Technologies, AI & Robotics Chapter 8: Modeling, Computer Graphics and Big Data in Energy Management Chapter 9: Monitoring and control of Smart Buildings, including Smart Grid interoperability Chapter 10: Basics and Emergence of Environmental and Energy Informatics Chapter 11: Emerging and Intelligent Systems in Environment and Ecology Chapter 12: Building product disclosure and optimization: Effect on Ecological system Chapter 13: AI in waste management: The savage of Environment
£107.99
Springer Verlag, Singapore MCMC from Scratch: A Practical Introduction to
Book SynopsisThis textbook explains the fundamentals of Markov Chain Monte Carlo (MCMC) without assuming advanced knowledge of mathematics and programming. MCMC is a powerful technique that can be used to integrate complicated functions or to handle complicated probability distributions. MCMC is frequently used in diverse fields where statistical methods are important – e.g. Bayesian statistics, quantum physics, machine learning, computer science, computational biology, and mathematical economics. This book aims to equip readers with a sound understanding of MCMC and enable them to write simulation codes by themselves. The content consists of six chapters. Following Chap. 2, which introduces readers to the Monte Carlo algorithm and highlights the advantages of MCMC, Chap. 3 presents the general aspects of MCMC. Chap. 4 illustrates the essence of MCMC through the simple example of the Metropolis algorithm. In turn, Chap. 5 explains the HMC algorithm, Gibbs sampling algorithm and Metropolis-Hastings algorithm, discussing their pros, cons and pitfalls. Lastly, Chap. 6 presents several applications of MCMC. Including a wealth of examples and exercises with solutions, as well as sample codes and further math topics in the Appendix, this book offers a valuable asset for students and beginners in various fields. Table of ContentsChapter 1: Introduction.- Chapter 2: What is the Monte Carlo method?.- Chapter 3: General Aspects of Markov Chain Monte Carlo.- Chapter 4: Metropolis Algorithm.- Chapter 5: Other Useful Algorithms.- Chapter 6: Applications of Markov Chain Monte Carlo.
£40.49
Springer Verlag, Singapore MCMC from Scratch: A Practical Introduction to
Book SynopsisThis textbook explains the fundamentals of Markov Chain Monte Carlo (MCMC) without assuming advanced knowledge of mathematics and programming. MCMC is a powerful technique that can be used to integrate complicated functions or to handle complicated probability distributions. MCMC is frequently used in diverse fields where statistical methods are important – e.g. Bayesian statistics, quantum physics, machine learning, computer science, computational biology, and mathematical economics. This book aims to equip readers with a sound understanding of MCMC and enable them to write simulation codes by themselves. The content consists of six chapters. Following Chap. 2, which introduces readers to the Monte Carlo algorithm and highlights the advantages of MCMC, Chap. 3 presents the general aspects of MCMC. Chap. 4 illustrates the essence of MCMC through the simple example of the Metropolis algorithm. In turn, Chap. 5 explains the HMC algorithm, Gibbs sampling algorithm and Metropolis-Hastings algorithm, discussing their pros, cons and pitfalls. Lastly, Chap. 6 presents several applications of MCMC. Including a wealth of examples and exercises with solutions, as well as sample codes and further math topics in the Appendix, this book offers a valuable asset for students and beginners in various fields. Table of ContentsChapter 1: Introduction.- Chapter 2: What is the Monte Carlo method?.- Chapter 3: General Aspects of Markov Chain Monte Carlo.- Chapter 4: Metropolis Algorithm.- Chapter 5: Other Useful Algorithms.- Chapter 6: Applications of Markov Chain Monte Carlo.
£40.49
Springer Verlag, Singapore Deep Learning in Solar Astronomy
Book SynopsisThe volume of data being collected in solar astronomy has exponentially increased over the past decade and we will be entering the age of petabyte solar data. Deep learning has been an invaluable tool exploited to efficiently extract key information from the massive solar observation data, to solve the tasks of data archiving/classification, object detection and recognition. Astronomical study starts with imaging from recorded raw data, followed by image processing, such as image reconstruction, inpainting and generation, to enhance imaging quality. We study deep learning for solar image processing. First, image deconvolution is investigated for synthesis aperture imaging. Second, image inpainting is explored to repair over-saturated solar image due to light intensity beyond threshold of optical lens. Third, image translation among UV/EUV observation of the chromosphere/corona, Ha observation of the chromosphere and magnetogram of the photosphere is realized by using GAN, exhibiting powerful image domain transfer ability among multiple wavebands and different observation devices. It can compensate the lack of observation time or waveband. In addition, time series model, e.g., LSTM, is exploited to forecast solar burst and solar activity indices. This book presents a comprehensive overview of the deep learning applications in solar astronomy. It is suitable for the students and young researchers who are major in astronomy and computer science, especially interdisciplinary research of them.Trade Review“Each application is described with sufficient detail to give the reader an understanding of how AI is used and how its use compares with older tools used for the same purposes. The writing is clear … and an excessive use of acronyms. Relevant images and tables enhance the reader’s understanding; many references accompany each chapter. This book should appeal to those interested in either AI or the field of solar astronomy.” (G. R. Mayforth, Computing Reviews, November 22, 2023)Table of ContentsChapter 1: Introduction Chapter 2: Classical deep learning models Chapter 3: Deep learning in solar image classification tasks Chapter 4: Deep learning in solar object detection tasks · Active Region (AR) detection · EUV waves detection Chapter 5: Deep learning in solar image generation tasks · Deconvolution of aperture synthesis · Recovering over-exposed solar image · Generating magnetogram from EUV image · Generating magnetogram from H-alpha Chapter 6: Deep learning in solar forecasting tasks · Flare forecast · F10.7c forecast
£42.74
Springer Verlag, Singapore Intelligent Sustainable Systems: Proceedings of
Book SynopsisThis book features research papers presented at the 5th International Conference on Intelligent Sustainable Systems (ICISS 2022), held at SCAD College of Engineering and Technology, Tirunelveli, Tamil Nadu, India, during February 17–18, 2022. The book discusses latest research works that discusses the tools, methodologies, practices, and applications of sustainable systems and computational intelligence methodologies. The book is beneficial for readers from both academia and industry.Table of ContentsChapter 1. Lung Ultrasound Covid-19 Detection using Deep Feature Recursive Neural Network.- Chapter 2. Predicting New York Taxi Trip Duration based on Regression Analysis using ML and Time Series Forecasting using DL.- Chapter 3. Implementation of Classical Error Control Codes for Memory Storage Systems using VERILOG.- Chapter 4. Parkinson’s Disease Detection using Machine Learning.- Chapter 5. Sustainable Consumption: An Approach to Achieve the Sustainable Environment in India.- Chapter 6. The Concept of a Digital Marketing Communication Model for Higher Education Institutions.- Chapter 7. A Lightweight Image Colorization Model based on U-Net Architecture.- Chapter 8. Comparative Analysis of Obesity Level Estimation based on Life-Style using Machine Learning.- Chapter 9. An empirical Study on Millennials' Adoption of Mobile Wallets.- Chapter 10. AIoT Based Smart Mirror.- Chapter 11. AI Assisted College Recommendation System.- Chapter 12. An Agent-based Model to Predict the Emergence of Student Protests in Public Higher Education Institution.- Chapter 13. High Accuracy for Hyperspectral Image Classification using Hybrid Spectral 3-D-2-D CNN.- Chapter 14. Design Smart Curtain Using Light Dependent Resistor.- Chapter 15. Machine Learning Assisted Binary and Multiclass Parkinson's Disease Detection. etc.
£189.99
Springer Verlag, Singapore Data, Engineering and Applications: Select
Book SynopsisThe book contains select proceedings of the 3rd International Conference on Data, Engineering, and Applications (IDEA 2021). It includes papers from experts in industry and academia that address state-of-the-art research in the areas of big data, data mining, machine learning, data science, and their associated learning systems and applications. This book will be a valuable reference guide for all graduate students, researchers, and scientists interested in exploring the potential of big data applications.Table of Contents1. Medical Assistance Chatbot using Deep Learning.- 2. Distortion Controlled Secure Reversible Data Hiding in H.264 videos.- 3. A Method for improving Efficiency and Security of FANET using Chaotic Black Hole Optimization based Routing (BHOR) Technique.- 4. Machine Learning Techniques for Intrusion Detection System: A Survey.- 5. Software Fault Detection by using Rider Optimization Algorithm (ROA) based Deep Neural Network (DNN).- 6. An Approach for Predicting Admissions in Post Graduate Program by using Machine Learning.- 7. A Survey on Various Representation Learning of Hypergraph for Unsupervised Feature Selection.- 8. A brief study of time series forecasting technique using linear regression, SVM, LSTM, ARIMA and SARIMA.- 9. Adoption of Blockchain Technology for Storage & Verification of Educational Documents.- 10. Obstacle Collision Prediction model for Path Planning Using Obstacle Trajectory Clustering.
£116.99
Springer Verlag, Singapore Intelligent System Design: Proceedings of INDIA
Book SynopsisThis book presents a collection of high-quality, peer-reviewed research papers from the 7th International Conference on Information System Design and Intelligent Applications (India 2022), held at BVRIT Hyderabad College of Engineering for Women, Hyderabad, Telangana, India, from February 25 to 26, 2022. It covers a wide range of topics in computer science and information technology, including data mining and data warehousing, high-performance computing, parallel and distributed computing, computational intelligence, soft computing, big data, cloud computing, grid computing and cognitive computing.
£189.99
Springer Verlag, Singapore Machine Learning, Image Processing, Network
Book SynopsisThis book constitutes the refereed proceedings of the Third International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2021. The papers are organized according to the following topical sections: data science and big data; image processing and computer vision; machine learning and computational intelligence; network and cybersecurity. This book aims to develop an understanding of image processing, networks, and data modeling by using various machine learning algorithms for a wide range of real-world applications. In addition to providing basic principles of data processing, this book teaches standard models and algorithms for data and image analysis. Table of ContentsA Methodological review of Time Series Forecasting with Deep Learning Model : A Case study on Electricity Load and Price Prediction.- A Robust Secure Access Entrance Method Based on Multi Model Biometric Credentials Iris and Finger Print.- Prostate Cancer Grading using Multistage DeepNeural Networks.
£170.99
Springer Verlag, Singapore Proceedings of 3rd International Conference on
Book SynopsisThe book is a collection of best selected research papers presented at the International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications (ICMISC 2022) held during 28 – 29 March 2022 at CMR Institute of Technology, Hyderabad, Telangana, India. This book will contain the articles on current trends of machine learning, internet of things, and smart cities applications emphasizing on multi-disciplinary research in the area of artificial intelligence and cyber physical systems. The book is a great resource for scientists, research scholars and PG students to formulate their research ideas and find the future directions in these areas. Further, this book serves as a reference work to understand the latest technologies by practice engineers across the globe.Table of ContentsPrognostic Investigation into Melancholic Maladies in Hinterlands.- Security Threats in Healthcare Systems.- A Review on Behavioral Biometric GAIT Recognition.- Vital Role of 2D CNN in Brain Malignancy.- Design and Development of IoT based Intelligent Cattle Shed Management.- Review Paper on Technologies to curb Noise Pollution in No Honking Zones.- Radial Basis Neural Network Trained Minimum Snap Trajectory for Quadrotor.- Detection of Fraudulent Credit Card Transactions in Real-Time using SparkML and Kafka.- Robust and Scalable Network Monitoring System using Apache Spark.- Managing data protection and privacy on cloud.- Human Posture Monitoring.- Automation in Project Management 4.0 with Artificial Intelligence.- A state of art Approach to Question Generation Techniques.- Intelligent Information System for Detection of Covid-19 based on AI.- Plant Quality Assessment and Disease Identification System using AI.- Image-based Plant Disease Detection and classification using Deep Convolution Neural Network.
£179.99
Springer Verlag, Singapore Machine Learning Safety
Book SynopsisMachine learning algorithms allow computers to learn without being explicitly programmed. Their application is now spreading to highly sophisticated tasks across multiple domains, such as medical diagnostics or fully autonomous vehicles. While this development holds great potential, it also raises new safety concerns, as machine learning has many specificities that make its behaviour prediction and assessment very different from that for explicitly programmed software systems. This book addresses the main safety concerns with regard to machine learning, including its susceptibility to environmental noise and adversarial attacks. Such vulnerabilities have become a major roadblock to the deployment of machine learning in safety-critical applications. The book presents up-to-date techniques for adversarial attacks, which are used to assess the vulnerabilities of machine learning models; formal verification, which is used to determine if a trained machine learning model is free of vulnerabilities; and adversarial training, which is used to enhance the training process and reduce vulnerabilities. The book aims to improve readers’ awareness of the potential safety issues regarding machine learning models. In addition, it includes up-to-date techniques for dealing with these issues, equipping readers with not only technical knowledge but also hands-on practical skills.Table of Contents1. Introduction.- 2. Safety of Simple Machine Learning Models.- 3. Safety of Deep Learning.- 4. Robustness Verification of Deep Learning.- 5. Enhancement to Robustness and Generalization.- 6. Probabilistic Graph Model.- A. Mathematical Foundations.- B. Competitions.-
£53.99
Springer Verlag, Singapore Computer Vision and Machine Intelligence
Book SynopsisThis book constitutes refereed proceedings of the 4th International Conference on Recent Trends in Advanced Computing - Computer Vision and Machine Intelligence Paradigms for Sustainable Development Goals. This book covers novel and state-of-the-art methods in computer vision coupled with intelligent techniques including machine learning, deep learning, and soft computing techniques. The contents of this book will be useful to researchers from industry and academia. This book includes contemporary innovations, trends, and concerns in computer vision with recommended solutions to real-world problems adhering to sustainable development from researchers across industry and academia. This book serves as a valuable reference resource for academics and researchers across the globe.Table of ContentsPTZ-camera-based facial expression analysis using faster R-CNN for student engagement recognitionConvergence Perceptual Model for Computing Time-Series-Data on Fog-EnvironmentLocalized Super Resolution for Foreground Images using U-Net and MR-CNNSMS Spam Classification Using PSO-C4.5Automated Sorting, Grading of Fruits Based on Internal and External Quality Assessment Using HSI, Deep CNNPest Detection using Improvised YOLO ArchitectureClassification of Fungi Effected Psidium Guajava Leaves using ML and DL TechniquesDeep Learning Based Recognition of Plant DiseasesArtificial Cognition of Temporal Events using Recurrent Point Process NetworksOn the Performance of Energy Efficient Video Transmission over LEACH based protocol in WSNHybridization of Texture Features for Identification of Bi-lingual Scripts from Camera Images at WordlevelAdvanced Algorithmic Techniques for Topic Prediction and Recommendation - An AnalysisImplementation of an automatic EEG feature extraction with Gated Recurrent Neural Network for Emotion Recognition.
£170.99
Springer Verlag, Singapore IoT and AI in Agriculture: Self- sufficiency in
Book SynopsisThis book reviews recent innovations in the smart agriculture space that use the Internet of Things (IoT) and sensing to deliver Artificial Intelligence (AI) solutionsto agricultural productivity in the agricultural production hubs. In this regard, South and Southeast Asia are one of the major agricultural hubs of the world, facing challenges of climate change and feeding the fast-growing population. To address such challenges, a transboundary approach along with AI and BIG data for bioinformatics are required to increase yield and minimize pre- and post-harvest losses in intangible climates to drive the sustainable development goal (SDG) for feeding a major part of the 9 billion population by 2050 (Society 5.0 SDG 1 & 2). Therefore, this book focuses on the solution through smart IoT and AI-based agriculture including pest infestation and minimizing agricultural inputs for in-house and fields production such as light, water, fertilizer and pesticides to ensure food security aligns with environmental sustainability. It provides a sound understanding for creating new knowledge in line with comprehensive research and education orientation on how the deployment of tiny sensors, AI/Machine Learning (ML), controlled UAVs, and IoT setups for sensing, tracking, collection, processing, and storing information over cloud platforms for nurturing and driving the pace of smart agriculture in this current time. The book will appeal to several audiences and the contents are designed for researchers, graduates, and undergraduate students working in any area of machine learning, deep learning in agricultural engineering, smart agriculture, and environmental science disciplines. Utmost care has been taken to present a varied range of resource areas along with immense insights into the impact and scope of IoT, AI and ML in the growth of intelligent digital farming and smart agriculture which will give comprehensive information to the targeted readers. Table of ContentsChapter 1. IoT x AI: Introducing Agricultural Innovation for Global Food Production.- Chapter 2. Transforming Controlled Environment Plant Production toward Circular Bioeconomy Systems.- Chapter 3. Artificial Lighting Systems for Plant Growth and Development in Indoor Farming.- Chapter 4. An IoT-based Precision Irrigation System to Optimize Plant Water Requirements for Indoor and Outdoor Farming Systems.- Chapter 5. Artificial Intelligence & Internet of Things: Application in Urban Water Management.- Chapter 6.Purification of Agricultural Polluted Water Using Solar Distillation and Hot Water Producing with Continuous Monitoring Based on IoT.- Chapter 7. Long Range Wide Area Network (LoRaWAN) for Oil Palm Soil Monitoring.- Chapter 8. Application of Smart Machine Vision in Agriculture, Forestry, Fishery, and Animal Husbandry.- Chapter 9. Artificial Intelligence in Agriculture: Commitment to Establish Society 5.0 .- Chapter 10. Potentials of Deep Learning Frameworks for Tree Trunk Detection in Orchard to Enable Autonomous Navigation System.- Chapter 11. Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT.- Chapter 12. Pear Recognition in an Orchard from 3D Stereo Camera Datasets to Develop an Autonomous Mechanism Compared with Deep Learning Algorithms.- Chapter 13. Thermal Imaging and Deep Learning Object Detection Algorithms for Early Embryo Detection – A Methodology Development Addressed to Quail Precision Hatching.- Chapter 14. Intelligent Sensing and Robotic Picking of Kiwifruit in Orchard.- Chapter 15. Low-cost Automatic Machinery Development to Increase Timeliness and Efficiency of Operation for Small Scale Farmers to Achieve SDGs.- Chapter 16. Vision-based Leader Vehicle Trajectory Tracking for Multiple Agricultural Vehicles.- Chapter 17. Autonomous Robots in Orchard Management: Present status and future trends.- Chapter 18. Comparing Soil Moisture Retrieval from Water Cloud Model and Neural Network Using PALSAR-2 for Oil Palm Estates.- Chapter 19. Development of a Recognition System for Spraying Areas from Unmanned Aerial Vehicles Using a Machine Learning Approach.- Chapter 20. Basal Stem Rot Disease Classification by Machine Learning Using Thermal Images and an Imbalanced Data Approach.- Chapter 21. Early Detection of Plant Disease Infection using Hyperspectral Data and Machine Learning.- Chapter 22. The Spectrum of Autonomous Machinery Development to Increase Agricultural Productivity for Achieving Society 5.0 in Japan.
£127.49
Springer Verlag, Singapore Distributed Optimization in Networked Systems:
Book SynopsisThis book focuses on improving the performance (convergence rate, communication efficiency, computational efficiency, etc.) of algorithms in the context of distributed optimization in networked systems and their successful application to real-world applications (smart grids and online learning). Readers may be particularly interested in the sections on consensus protocols, optimization skills, accelerated mechanisms, event-triggered strategies, variance-reduction communication techniques, etc., in connection with distributed optimization in various networked systems. This book offers a valuable reference guide for researchers in distributed optimization and for senior undergraduate and graduate students alike.Table of ContentsChapter 1. Distributed Nesterov-Like Accelerated Algorithms in Networked Systems with Directed Communications.- Chapter 2. Distributed Stochastic Projected Gradient Algorithms for Composite Constrained Optimization in Networked Systems.- Chapter 3. Distributed Proximal Stochastic Gradient Algorithms for Coupled Composite Optimization in Networked Systems.- Chapter 4. Distributed Subgradient Algorithms Based on Event-Triggered Strategy in Networked Systems.- Chapter 5. Distributed Accelerated Stochastic Algorithms Based on Event-Triggered Strategy in Networked Systems.- Chapter 6. Event-Triggered Based Distributed Optimal Economic Dispatch in Smart Grids.- Chapter 7. Fast Distributed Optimal Economic Dispatch in Dynamic Smart Grids with Directed Communications.- Chapter 8. Accelerated Distributed Optimal Economic Dispatch in Smart Grids with Directed Communications.- Chapter 9. Privacy Preserving Distributed Online Learning with Time-Varying and Directed Communications.
£125.99
