Reinforcement and Systemic Machine Learning for Decision Making
There are always difficulties in making machines that learn from experience. Complete information is not always available—or it becomes available in bits and pieces over a period of time. With respect to systemic learning, there is a need to understand the impact of decisions and actions on a system over that period of time. This book takes a holistic approach to addressing that need and presents a new paradigm—creating new learning applications and, ultimately, more intelligent machines.
The first book of its kind in this new and growing field, Reinforcement and Systemic Machine Learning for Decision Making focuses on the specialized research area of machine learning and systemic machine learning. It addresses reinforcement learning and its applications, incremental machine learning, repetitive failure-correction mechanisms, and multiperspective decision making.
Chapters include:
Introduction to Reinforcement and Systemic Machine Learning Fundamentals of Whole-System, Systemic, and Multiperspective Machine Learning Systemic Machine Learning and Model Inference and Information Integration Adaptive Learning Incremental Learning and Knowledge Representation Knowledge Augmentation: A Machine Learning Perspective Building a Learning System With the potential of this paradigm to become one of the more utilized in its field, professionals in the area of machine and systemic learning will find this book to be a valuable resource.
By:
Parag Kulkarni,
Bithika Samanta
Imprint: Wiley-IEEE Press
Country of Publication: United States
Dimensions:
Height: 241mm,
Width: 165mm,
Spine: 20mm
Weight: 562g
ISBN: 9780470919996
ISBN 10: 047091999X
Series: IEEE Press Series on Systems Science and Engineering
Pages: 320
Publication Date: 30 July 2012
Audience:
Professional and scholarly
,
Undergraduate
Format: Hardback
Publisher's Status: Active
Preface xv Acknowledgments xix About the Author xxi 1 Introduction to Reinforcement and Systemic Machine Learning 1 1.1. Introduction 1 1.2. Supervised, Unsupervised, and Semisupervised Machine Learning 2 1.3. Traditional Learning Methods and History of Machine Learning 4 1.4. What Is Machine Learning? 7 1.5. Machine-Learning Problem 8 1.6. Learning Paradigms 9 1.7. Machine-Learning Techniques and Paradigms 12 1.8. What Is Reinforcement Learning? 14 1.9. Reinforcement Function and Environment Function 16 1.10. Need of Reinforcement Learning 17 1.11. Reinforcement Learning and Machine Intelligence 17 1.12. What Is Systemic Learning? 18 1.13. What Is Systemic Machine Learning? 18 1.14. Challenges in Systemic Machine Learning 19 1.15. Reinforcement Machine Learning and Systemic Machine Learning 19 1.16. Case Study Problem Detection in a Vehicle 20 1.17. Summary 20 2 Fundamentals of Whole-System, Systemic, and Multiperspective Machine Learning 23 2.1. Introduction 23 2.2. What Is Systemic Machine Learning? 27 2.3. Generalized Systemic Machine-Learning Framework 30 2.4. Multiperspective Decision Making and Multiperspective Learning 33 2.5. Dynamic and Interactive Decision Making 43 2.6. The Systemic Learning Framework 47 2.7. System Analysis 52 2.8. Case Study: Need of Systemic Learning in the Hospitality Industry 54 2.9. Summary 55 3 Reinforcement Learning 57 3.1. Introduction 57 3.2. Learning Agents 60 3.3. Returns and Reward Calculations 62 3.4. Reinforcement Learning and Adaptive Control 63 3.5. Dynamic Systems 66 3.6. Reinforcement Learning and Control 68 3.7. Markov Property and Markov Decision Process 68 3.8. Value Functions 69 3.8.1. Action and Value 70 3.9. Learning an Optimal Policy (Model-Based and Model-Free Methods) 70 3.10. Dynamic Programming 71 3.11. Adaptive Dynamic Programming 71 3.12. Example: Reinforcement Learning for Boxing Trainer 75 3.13. Summary 75 4 Systemic Machine Learning and Model 77 4.1. Introduction 77 4.2. A Framework for Systemic Learning 78 4.3. Capturing the Systemic View 86 4.4. Mathematical Representation of System Interactions 89 4.5. Impact Function 91 4.6. Decision-Impact Analysis 91 4.7. Summary 97 5 Inference and Information Integration 99 5.1. Introduction 99 5.2. Inference Mechanisms and Need 101 5.3. Integration of Context and Inference 107 5.4. Statistical Inference and Induction 111 5.5. Pure Likelihood Approach 112 5.6. Bayesian Paradigm and Inference 113 5.7. Time-Based Inference 114 5.8. Inference to Build a System View 114 5.9. Summary 118 6 Adaptive Learning 119 6.1. Introduction 119 6.2. Adaptive Learning and Adaptive Systems 119 6.3. What Is Adaptive Machine Learning? 123 6.4. Adaptation and Learning Method Selection Based on Scenario 124 6.5. Systemic Learning and Adaptive Learning 127 6.6. Competitive Learning and Adaptive Learning 140 6.7. Examples 146 6.8. Summary 149 7 Multiperspective and Whole-System Learning 151 7.1. Introduction 151 7.2. Multiperspective Context Building 152 7.3. Multiperspective Decision Making and Multiperspective Learning 154 7.4. Whole-System Learning and Multiperspective Approaches 164 7.5. Case Study Based on Multiperspective Approach 167 7.6. Limitations to a Multiperspective Approach 174 7.7. Summary 174 8 Incremental Learning and Knowledge Representation 177 8.1. Introduction 177 8.2. Why Incremental Learning? 178 8.3. Learning from What Is Already Learned. . . 180 8.4. Supervised Incremental Learning 191 8.5. Incremental Unsupervised Learning and Incremental Clustering 191 8.6. Semisupervised Incremental Learning 196 8.7. Incremental and Systemic Learning 199 8.8. Incremental Closeness Value and Learning Method 200 8.9. Learning and Decision-Making Model 205 8.10. Incremental Classification Techniques 206 8.11. Case Study: Incremental Document Classification 207 8.12. Summary 208 9 Knowledge Augmentation: A Machine Learning Perspective 209 9.1. Introduction 209 9.2. Brief History and Related Work 211 9.3. Knowledge Augmentation and Knowledge Elicitation 215 9.4. Life Cycle of Knowledge 217 9.5. Incremental Knowledge Representation 222 9.6. Case-Based Learning and Learning with Reference to Knowledge Loss 224 9.7. Knowledge Augmentation: Techniques and Methods 224 9.8. Heuristic Learning 228 9.9. Systemic Machine Learning and Knowledge Augmentation 229 9.10. Knowledge Augmentation in Complex Learning Scenarios 232 9.11. Case Studies 232 9.12. Summary 235 10 Building a Learning System 237 10.1. Introduction 237 10.2. Systemic Learning System 237 10.3. Algorithm Selection 242 10.4. Knowledge Representation 244 10.5. Designing a Learning System 245 10.6. Making System to Behave Intelligently 246 10.7. Example-Based Learning 246 10.8. Holistic Knowledge Framework and Use of Reinforcement Learning 246 10.9. Intelligent Agents—Deployment and Knowledge Acquisition and Reuse 250 10.10. Case-Based Learning: Human Emotion-Detection System 251 10.11. Holistic View in Complex Decision Problem 253 10.12. Knowledge Representation and Data Discovery 255 10.13. Components 258 10.14. Future of Learning Systems and Intelligent Systems 259 10.15. Summary 259 Appendix A: Statistical Learning Methods 261 Appendix B: Markov Processes 271 Index 281
Parag Kulkarni, PhD, DSc, is the founder and Chief Scientist of EKLat Research where he has empowered businesses through machine learning, knowledge management, and systemic management. He has been working within the IT industry for over twenty years. The recipient of several awards, Dr. Kulkarni is a pioneer in the field. His areas of research and product development include M-maps, intelligent systems, text mining, image processing, decision systems, forecasting, IT strategy, artificial intelligence, and machine learning. Dr. Kulkarni has over 100 research publications including several books.
