國立虎尾科技大學 |

Reinforcement and systemic machine learning for decision making

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Reinforcement and systemic machine learning for decision making/ Parag Kulkarni.
Author:	Kulkarni, Parag.
Published:	Hoboken :John Wiley & Sons, : 2012.,
Description:	1 online resource (422 p.)
Subject:	Reinforcement learning. -
Online resource:	http://onlinelibrary.wiley.com/book/10.1002/9781118266502
ISBN:	9781118266502 (electronic bk.)

Reinforcement and systemic machine learning for decision making
Kulkarni, Parag.

Reinforcement and systemic machine learning for decision making[electronic resource] /Parag Kulkarni. - Hoboken :John Wiley & Sons,2012. - 1 online resource (422 p.) - IEEE Press Series on Systems Science and Engineering ;v.1. - IEEE Press series on systems science and engineering..

Introduction to Reinforcement and Systemic Machine Learning --ch. 1:

Reinforcement and Systemic Machine Learning for Decision MakingThere 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 g.

ISBN: 9781118266502 (electronic bk.)

Standard No.: 9786613807076Subjects--Topical Terms:

815404
Reinforcement learning.

LC Class. No.: Q325.6 / .K85 2012

Dewey Class. No.: 006.31

Reinforcement and systemic machine learning for decision making
LDR:07273cam a2200433Mu 4500 001 830931
003 OCoLC
005 20130709122842.0
006 m o d
007 cr |||||||||||
008 160215s2012 nju o 000 0 eng d
020 $a 9781118266502 (electronic bk.)
020 $a 1118266501 (electronic bk.)
020 $a 9781118271537 (electronic bk.)
020 $a 111827153X (electronic bk.)
020 $z 9780470919996
020 $a 047091999X
024 8 $a 9786613807076
035 $a (OCoLC)801366216
035 $a ocn801366216
040 $a EBLCP $b eng $c EBLCP $d OCLCQ $d N $d DG1 $d COO $d YDXCP $d OCLCQ $d OCLCO $d IEEEE $d ZMC $d DEBSZ
050 4 $a Q325.6 $b .K85 2012
082 0 4 $a 006.31 $a 006.31
100 1 $a Kulkarni, Parag. $3 880917
245 1 0 $a Reinforcement and systemic machine learning for decision making $h [electronic resource] / $c Parag Kulkarni.
260 $a Hoboken : $b John Wiley & Sons, $c 2012.
300 $a 1 online resource (422 p.)
490 1 $a IEEE Press Series on Systems Science and Engineering ; $v v.1
505 0 0 $g ch. 1: $t Introduction to Reinforcement and Systemic Machine Learning -- $g 1.1. $t Introduction -- $g 1.2. $t Supervised, Unsupervised, and Semisupervised Machine Learning -- $g 1.3. $t Traditional Learning Methods and History of Machine Learning -- $g 1.4. $t What is Machine Learning? -- $g 1.5. $t Machine-Learning Problem -- $g 1.6. $t Learning Paradigms -- $g 1.7. $t Machine-Learning Techniques and Paradigms -- $g 1.8. $t What is Reinforcement Learning? -- $g 1.9. $t Reinforcement Function and Environment Function -- $g 1.10. $t Need of Reinforcement Learning -- $g 1.11. $t Reinforcement Learning and Machine Intelligence -- $g 1.12. $t What is Systemic Learning? -- $g 1.13. $t What Is Systemic Machine Learning? -- $g 1.14. $t Challenges in Systemic Machine Learning -- $g 1.15. $t Reinforcement Machine Learning and Systemic Machine Learning -- $g 1.16. $t Case Study Problem Detection in a Vehicle -- $g 1.17. $t Summary -- $g Reference --
505 8 0 $g ch. 2: $t Fundamentals of Whole-System, Systemic, and Multiperspective Machine Learning -- $g 2.1. $t Introduction -- $g 2.2. $t What is Systemic Machine Learning? -- $g 2.3. $t Generalized Systemic Machine-Learning Framework -- $g 2.4. $t Multiperspective Decision Making and Multiperspective Learning -- $g 2.5. $t Dynamic and Interactive Decision Making -- $g 2.6. $t The Systemic Learning Framework -- $g 2.7. $t System Analysis -- $g 2.8. $t Case Study: $t Need of Systemic Learning in the Hospitality Industry -- $g 2.9. $t Summary --
505 8 0 $g ch. 3. $t : $t Reinforcement Learning -- $g 3.1. $t Introduction -- $g 3.2. $t Learning Agents -- $g 3.3. $t Returns and Reward Calculations -- $g 3.4. $t Reinforcement Learning and Adaptive Control -- $g 3.5. $t Dynamic Systems -- $g 3.6. $t Reinforcement Learning and Control -- $g 3.7. $t Markov Property and Markov Decision Process -- $g 3.8. $t Value Functions -- $g 3.9. $t Learning An Optimal Policy (Model-Based and Model-Free Methods) -- $g 3.10. $t Dynamic Programming -- $g 3.11. $t Adaptive Dynamic Programming -- $g 3.12. $t Example: $t Reinforcement Learning for Boxing Trainer -- $g 3.13. $t Summary -- $g Reference --
505 8 0 $g ch. 4: $t Systemic Machine Learning and Model -- $g 4.1. $t Introduction -- $g 4.2. $t A Framework for Systemic Learning -- $g 4.3. $t Capturing THE Systemic View -- $g 4.4. $t Mathematical Representation of System Interactions -- $g 4.5. $t Impact Function -- $g 4.6. $t Decision-Impact Analysis -- $g 4.7. $t Summary --
505 8 0 $g ch. 5: $t Inference and Information Integration -- $g 5.1. $t Introduction -- $g 5.2. $t Inference Mechanisms and Need -- $g 5.3. $t Integration of Context and Inference -- $g 5.4. $t Statistical Inference and Induction -- $g 5.5. $t Pure Likelihood Approach -- $g 5.6. $t Bayesian Paradigm and Inference -- $g 5.7. $t Time-Based Inference -- $g 5.8. $t Inference to Build a System View -- $g 5.9. $t Summary --
505 8 0 $g ch. 6: $t Adaptive Learning -- $g 6.1. $t Introduction -- $g 6.2. $t Adaptive Learning and Adaptive Systems -- $g 6.3. $t What is Adaptive Machine Learning? -- $g 6.4. $t Adaptation and Learning Method Selection Based on Scenario -- $g 6.5. $t Systemic Learning and Adaptive Learning -- $g 6.6. $t Competitive Learning and Adaptive Learning -- $g 6.7. $t Examples -- $g 6.8. $t Summary --
505 8 0 $g ch. 7: $t Multiperspective and Whole-System Learning -- $g 7.1. $t Introduction -- $g 7.2. $t Multiperspective Context Building -- $g 7.3. $t Multiperspective Decision Making and Multiperspective Learning -- $g 7.4. $t Whole-System Learning and Multiperspective Approaches -- $g 7.5. $t Case Study Based on Multiperspective Approach -- $g 7.6. $t Limitations to a Multiperspective Approach -- $g 7.7. $t Summary --
505 8 0 $g ch. 8: $t Incremental Learning and Knowledge Representation -- $g 8.1. $t Introduction -- $g 8.2. $t Why Incremental Learning? -- $g 8.3. $t Learning from What Is Already Learned -- $g 8.4. $t Supervised Incremental Learning -- $g 8.5. $t Incremental Unsupervised Learning and Incremental Clustering -- $g 8.6. $t Semisupervised Incremental Learning -- $g 8.7. $t Incremental and Systemic Learning -- $g 8.8. $t Incremental Closeness Value and Learning Method -- $g 8.9. $t Learning and Decision-Making Model -- $g 8.10. $t Incremental Classification Techniques -- $g 8.11. $t Case Study: Incremental Document Classification -- $g 8.12. $t Summary --
505 8 0 $g ch. 9 Knowledge Augmentation: A Machine Learning Perspective -- $g 9.1. $t Introduction -- $g 9.2. $t Brief History and Related Work -- $g 9.3. $t Knowledge Augmentation and Knowledge Elicitation -- $g 9.4. $t Life Cycle of Knowledge -- $g 9.5. $t Incremental Knowledge Representation -- $g 9.6. $t Case-Based Learning and Learning with Reference Knowledge Loss -- $g 9.7. $t Knowledge Augmentation: Techniques and Methods -- $g 9.8. $t Heuristic Learning -- $g 9.9. $t Systemic Machine Learning and Knowledge Augmentation -- $g 9.10. $t Knowledge Augmentation in Complex Learning Scenarios -- $g 9.11. $t Case Studies -- $g 9.12. $t Summary --
505 8 0 $g ch. 10: $t Building a Learning System -- $g 10.1. $t Introduction -- $g 10.2. $t Systemic Learning System -- $g 10.3. $t Algorithm Selection -- $g 10.4. $t Knowledge Representation -- $g 10.4.1. $t Practical Scenarios and Case Study -- $g 10.5. $t Designing a Learning System -- $g 10.6. $t Making System to Behave Intelligently -- $g 10.7. $t Example-Based Learning -- $g 10.8. $t Holistic Knowledge Framework and Use of Reinforcement Learning -- $g 10.9. $t Intelligent Agents Deployment and Knowledge Acquisition and Reuse -- $g 10.10. $t Case-Based Learning: Human Emotion-Detection System -- $g 10.11. $t Holistic View in Complex Decision Problem -- $g 10.12. $t Knowledge Representation and Data Discovery -- $g 10.13. $t Components -- $g 10.14. $t Future of Learning Systems and Intelligent Systems -- $g 10.15. $t Summary -- $g Appendix A: $t Statistical Learning Methods -- $g Appendix B: $t Markov Processes.
520 $a Reinforcement and Systemic Machine Learning for Decision MakingThere 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 g.
588 $a Description based upon print version of record.
650 0 $a Reinforcement learning. $3 815404
650 0 $a Machine learning. $3 561253
650 0 $a Decision making. $3 528319
830 0 $a IEEE Press series on systems science and engineering. $3 880918
856 4 0 $u http://onlinelibrary.wiley.com/book/10.1002/9781118266502