Atjaunināt sīkdatņu piekrišanu

Reinforcement and Systemic Machine Learning for Decision Making [Hardback]

3.40/5 (10 ratings by Goodreads)
  • Formāts: Hardback, 320 pages, height x width x depth: 241x165x20 mm, weight: 562 g, Photos: 10 B&W, 0 Color; Drawings: 90 B&W, 0 Color; Tables: 20 B&W, 0 Color
  • Sērija : IEEE Press Series on Systems Science and Engineering
  • Izdošanas datums: 04-Sep-2012
  • Izdevniecība: Wiley-IEEE Press
  • ISBN-10: 047091999X
  • ISBN-13: 9780470919996
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 145,68 €
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
  • Bibliotēkām
Reinforcement and Systemic Machine Learning for Decision MakingPalielināt
  • Formāts: Hardback, 320 pages, height x width x depth: 241x165x20 mm, weight: 562 g, Photos: 10 B&W, 0 Color; Drawings: 90 B&W, 0 Color; Tables: 20 B&W, 0 Color
  • Sērija : IEEE Press Series on Systems Science and Engineering
  • Izdošanas datums: 04-Sep-2012
  • Izdevniecība: Wiley-IEEE Press
  • ISBN-10: 047091999X
  • ISBN-13: 9780470919996
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9780470919996.html
Keywords:
Reinforcement and Systemic Machine Learning for Decision Making There are always difficulties in making machines that learn from experience. Complete information is not always availableor 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 paradigmcreating 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.
Preface xv
Acknowledgments xix
About the Author xxi
1 Introduction to Reinforcement and Systemic Machine Learning
1(22)
1.1 Introduction
1(1)
1.2 Supervised, Unsupervised, and Semisupervised Machine Learning
2(2)
1.3 Traditional Learning Methods and History of Machine Learning
4(3)
1.4 What Is Machine Learning?
7(1)
1.5 Machine-Learning Problem
8(1)
1.5.1 Goals of Learning
8(1)
1.6 Learning Paradigms
9(3)
1.7 Machine-Learning Techniques and Paradigms
12(2)
1.8 What Is Reinforcement Learning?
14(2)
1.9 Reinforcement Function and Environment Function
16(1)
1.10 Need of Reinforcement Learning
17(1)
1.11 Reinforcement Learning and Machine Intelligence
17(1)
1.12 What Is Systemic Learning?
18(1)
1.13 What Is Systemic Machine Learning?
18(1)
1.14 Challenges in Systemic Machine Learning
19(1)
1.15 Reinforcement Machine Learning and Systemic Machine Learning
19(1)
1.16 Case Study Problem Detection in a Vehicle
20(1)
1.17 Summary
20(3)
Reference
21(2)
2 Fundamentals of Whole-System, Systemic, and Multiperspective Machine Learning
23(34)
2.1 Introduction
23(4)
2.1.1 What Is Systemic Learning?
24(2)
2.1.2 History
26(1)
2.2 What Is Systemic Machine Learning?
27(3)
2.2.1 Event-Based Learning
29(1)
2.3 Generalized Systemic Machine-Learning Framework
30(3)
2.3.1 System Definition
31(2)
2.4 Multiperspective Decision Making and Multiperspective Learning
33(10)
2.4.1 Representation Based on Complete Information
40(1)
2.4.2 Representation Based on Partial Information
41(1)
2.4.3 Uni-Perspective Decision Scenario Diagram
41(1)
2.4.4 Dual-Perspective Decision Scenario Diagrams
41(1)
2.4.5 Multiperspective Representative Decision Scenario Diagrams
42(1)
2.4.6 Qualitative Belief Network and ID
42(1)
2.5 Dynamic and Interactive Decision Making
43(4)
2.5.1 Interactive Decision Diagrams
43(1)
2.5.2 Role of Time in Decision Diagrams and Influence Diagrams
43(1)
2.5.3 Systemic View Building
44(1)
2.5.4 Integration of Information
45(1)
2.5.5 Building Representative DSD
45(1)
2.5.6 Limited Information
45(1)
2.5.7 Role of Multiagent System in Systemic Learning
46(1)
2.6 The Systemic Learning Framework
47(5)
2.6.1 Mathematical Model
50(1)
2.6.2 Methods for Systemic Learning
50(1)
2.6.3 Adaptive Systemic Learning
51(1)
2.6.4 Systemic Learning Framework
52(1)
2.7 System Analysis
52(2)
2.8 Case Study: Need of Systemic Learning in the Hospitality Industry
54(1)
2.9 Summary
55(2)
References
56(1)
3 Reinforcement Learning
57(20)
3.1 Introduction
57(3)
3.2 Learning Agents
60(2)
3.3 Returns and Reward Calculations
62(1)
3.3.1 Episodic and Continuing Task
63(1)
3.4 Reinforcement Learning and Adaptive Control
63(3)
3.5 Dynamic Systems
66(2)
3.5.1 Discrete Event Dynamic System
67(1)
3.6 Reinforcement Learning and Control
68(1)
3.7 Markov Property and Markov Decision Process
68(1)
3.8 Value Functions
69(1)
3.8.1 Action and Value
70(1)
3.9 Learning an Optimal Policy (Model-Based and Model-Free Methods)
70(1)
3.10 Dynamic Programming
71(1)
3.10.1 Properties of Dynamic Systems
71(1)
3.11 Adaptive Dynamic Programming
71(4)
3.11.1 Temporal Difference (TD) Learning
71(3)
3.11.2 Q-Learning
74(1)
3.11.3 Unified View
74(1)
3.12 Example: Reinforcement Learning for Boxing Trainer
75(1)
3.13 Summary
75(2)
Reference
76(1)
4 Systemic Machine Learning and Model
77(22)
4.1 Introduction
77(1)
4.2 A Framework for Systemic Learning
78(8)
4.2.1 Impact Space
80(5)
4.2.2 Interaction-Centric Models
85(1)
4.2.3 Outcome-Centric Models
85(1)
4.3 Capturing the Systemic View
86(3)
4.4 Mathematical Representation of System Interactions
89(2)
4.5 Impact Function
91(1)
4.6 Decision-Impact Analysis
91(6)
4.6.1 Time and Space Boundaries
92(5)
4.7 Summary
97(2)
5 Inference and Information Integration
99(20)
5.1 Introduction
99(2)
5.2 Inference Mechanisms and Need
101(6)
5.2.1 Context Inference
103(1)
5.2.2 Inference to Determine Impact
103(4)
5.3 Integration of Context and Inference
107(4)
5.4 Statistical Inference and Induction
111(1)
5.4.1 Direct Inference
111(1)
5.4.2 Indirect Inference
112(1)
5.4.3 Informative Inference
112(1)
5.4.4 Induction
112(1)
5.5 Pure Likelihood Approach
112(1)
5.6 Bayesian Paradigm and Inference
113(1)
5.6.1 Bayes' Theorem
113(1)
5.7 Time-Based Inference
114(1)
5.8 Inference to Build a System View
114(4)
5.8.1 Information Integration
115(3)
5.9 Summary
118(1)
References
118(1)
6 Adaptive Learning
119(32)
6.1 Introduction
119(1)
6.2 Adaptive Learning and Adaptive Systems
119(4)
6.3 What Is Adaptive Machine Learning?
123(1)
6.4 Adaptation and Learning Method Selection Based on Scenario
124(3)
6.4.1 Dynamic Adaptation and Context-Aware Learning
125(2)
6.5 Systemic Learning and Adaptive Learning
127(13)
6.5.1 Use of Multiple Learners
129(3)
6.5.2 Systemic Adaptive Machine Learning
132(3)
6.5.3 Designing an Adaptive Application
135(1)
6.5.4 Need of Adaptive Learning and Reasons for Adaptation
135(1)
6.5.5 Adaptation Types
136(3)
6.5.6 Adaptation Framework
139(1)
6.6 Competitive Learning and Adaptive Learning
140(6)
6.6.1 Adaptation Function
142(2)
6.6.2 Decision Network
144(1)
6.6.3 Representation of Adaptive Learning Scenario
145(1)
6.7 Examples
146(3)
6.7.1 Case Study: Text-Based Adaptive Learning
147(1)
6.7.2 Adaptive Learning for Document Mining
148(1)
6.8 Summary
149(2)
References
149(2)
7 Multiperspective and Whole-System Learning
151(26)
7.1 Introduction
151(1)
7.2 Multiperspective Context Building
152(2)
7.3 Multiperspective Decision Making and Multiperspective Learning
154(10)
7.3.1 Combining Perspectives
155(1)
7.3.2 Influence Diagram and Partial Decision Scenario Representation Diagram
156(4)
7.3.3 Representative Decision Scenario Diagram (RDSD)
160(1)
7.3.4 Example: PDSRD Representations for City Information Captured from Different Perspectives
160(4)
7.4 Whole-System Learning and Multiperspective Approaches
164(3)
7.4.1 Integrating Fragmented Information
165(1)
7.4.2 Multiperspective and Whole-System Knowledge Representation
165(1)
7.4.3 What Are Multiperspective Scenarios?
165(1)
7.4.4 Context in Particular
166(1)
7.5 Case Study Based on Multiperspective Approach
167(7)
7.5.1 Traffic Controller Based on Multiperspective Approach
167(2)
7.5.2 Multiperspective Approach Model for Emotion Detection
169(5)
7.6 Limitations to a Multiperspective Approach
174(1)
7.7 Summary
174(3)
References
175(2)
8 Incremental Learning and Knowledge Representation
177(32)
8.1 Introduction
177(1)
8.2 Why Incremental Learning?
178(2)
8.3 Learning from What Is Already Learned...
180(11)
8.3.1 Absolute Incremental Learning
181(1)
8.3.2 Selective Incremental Learning
182(9)
8.4 Supervised Incremental Learning
191(1)
8.5 Incremental Unsupervised Learning and Incremental Clustering
191(5)
8.5.1 Incremental Clustering: Tasks
193(2)
8.5.2 Incremental Clustering: Methods
195(1)
8.5.3 Threshold Value
196(1)
8.6 Semisupervised Incremental Learning
196(3)
8.7 Incremental and Systemic Learning
199(1)
8.8 Incremental Closeness Value and Learning Method
200(5)
8.8.1 Approach 1 for Incremental Learning
201(1)
8.8.2 Approach 2
202(1)
8.8.3 Calculating C Values Incrementally
202(3)
8.9 Learning and Decision-Making Model
205(1)
8.10 Incremental Classification Techniques
206(1)
8.11 Case Study: Incremental Document Classification
207(1)
8.12 Summary
208(1)
9 Knowledge Augmentation: A Machine Learning Perspective
209(28)
9.1 Introduction
209(2)
9.2 Brief History and Related Work
211(4)
9.3 Knowledge Augmentation and Knowledge Elicitation
215(2)
9.3.1 Knowledge Elicitation by Strategy Used
215(1)
9.3.2 Knowledge Elicitation Based on Goals
216(1)
9.3.3 Knowledge Elicitation Based on Process
216(1)
9.4 Life Cycle of Knowledge
217(5)
9.4.1 Knowledge Levels
219(1)
9.4.2 Direct Knowledge
219(1)
9.4.3 Indirect Knowledge
219(1)
9.4.4 Procedural Knowledge
219(1)
9.4.5 Questions
220(1)
9.4.6 Decisions
220(1)
9.4.7 Knowledge Life Cycle
220(2)
9.5 Incremental Knowledge Representation
222(2)
9.6 Case-Based Learning and Learning with Reference to Knowledge Loss
224(1)
9.7 Knowledge Augmentation: Techniques and Methods
224(4)
9.7.1 Knowledge Augmentation Techniques
225(1)
9.7.2 Knowledge Augmentation Methods
226(1)
9.7.3 Mechanisms for Extracting Knowledge
227(1)
9.8 Heuristic Learning
228(1)
9.9 Systemic Machine Learning and Knowledge Augmentation
229(3)
9.9.1 Systemic Aspects of Knowledge Augmentation
230(1)
9.9.2 Systemic Knowledge Management and Advanced Machine Learning
231(1)
9.10 Knowledge Augmentation in Complex Learning Scenarios
232(1)
9.11 Case Studies
232(3)
9.11.1 Case Study Banking
232(1)
9.11.2 Software Development Firm
233(1)
9.11.3 Grocery Bazaar/Retail Bazaar
234(1)
9.12 Summary
235(2)
References
235(2)
10 Building a Learning System
237(24)
10.1 Introduction
237(1)
10.2 Systemic Learning System
237(5)
10.2.1 Learning Element
240(1)
10.2.2 Knowledge Base
240(1)
10.2.3 Performance Element
240(1)
10.2.4 Feedback Element
240(1)
10.2.5 System to Allow Measurement
241(1)
10.3 Algorithm Selection
242(2)
10.3.1 k-Nearest-Neighbor (k-NN)
242(1)
10.3.2 Support Vector Machine (SVM)
243(1)
10.3.3 Centroid Method
243(1)
10.4 Knowledge Representation
244(1)
10.4.1 Practical Scenarios and Case Study
244(1)
10.5 Designing a Learning System
245(1)
10.6 Making System to Behave Intelligently
246(1)
10.7 Example-Based Learning
246(1)
10.8 Holistic Knowledge Framework and Use of Reinforcement Learning
246(4)
10.8.1 Intelligent Algorithms Selection
249(1)
10.9 Intelligent Agents---Deployment and Knowledge Acquisition and Reuse
250(1)
10.10 Case-Based Learning: Human Emotion-Detection System
251(2)
10.11 Holistic View in Complex Decision Problem
253(2)
10.12 Knowledge Representation and Data Discovery
255(3)
10.13 Components
258(1)
10.13.1 Example
258(1)
10.14 Future of Learning Systems and Intelligent Systems
259(1)
10.15 Summary
259(2)
Appendix A Statistical Learning Methods 261(10)
Appendix B Markov Processes 271(10)
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.