Machine Learning: A Constraint-Based Approach
- Length: 580 pages
- Edition: 1
- Language: English
- Publisher: Morgan Kaufmann
- Publication Date: 2017-11-27
- ISBN-10: 0081006594
- ISBN-13: 9780081006597
- Sales Rank: #692309 (See Top 100 Books)
Machine Learning: A Constraint-Based Approach provides readers with a refreshing look at the basic models and algorithms of machine learning, with an emphasis on current topics of interest that includes neural networks and kernel machines.
The book presents the information in a truly unified manner that is based on the notion of learning from environmental constraints. While regarding symbolic knowledge bases as a collection of constraints, the book draws a path towards a deep integration with machine learning that relies on the idea of adopting multivalued logic formalisms, like in fuzzy systems. A special attention is reserved to deep learning, which nicely fits the constrained- based approach followed in this book.
This book presents a simpler unified notion of regularization, which is strictly connected with the parsimony principle, and includes many solved exercises that are classified according to the Donald Knuth ranking of difficulty, which essentially consists of a mix of warm-up exercises that lead to deeper research problems. A software simulator is also included.
- Presents fundamental machine learning concepts, such as neural networks and kernel machines in a unified manner
- Provides in-depth coverage of unsupervised and semi-supervised learning
- Includes a software simulator for kernel machines and learning from constraints that also includes exercises to facilitate learning
- Contains 250 solved examples and exercises chosen particularly for their progression of difficulty from simple to complex
Table of Contents
Chapter 1 The Big Picture
Chapter 2 Learning Principles
Chapter 3 Linear Threshold Machines
Chapter 4 Kernel Machines
Chapter 5 Deep Architectures
Chapter 6 Learning And Reasoning With Constraints
Chapter 7 Epilogue
Chapter 8 Answers To Exercises
Appendix A. Constrained Optimization In Finite Dimensions
Appendix B. Regularization Operators
Appendix C. Calculus Of Variations
Appendix D. Index To Notation
Cover image Title page Table of Contents Copyright Dedication Preface Acknowledgments Reading guidelines Notes on the Exercises Bibliography Chapter 1: The Big Picture Abstract 1.1. Why Do Machines Need to Learn? Exercises 1.2. Principles and Practice Exercises 1.3. Hands-on Experience Exercises 1.4. Challenges in Machine Learning Exercises 1.5. Scholia Bibliography Chapter 2: Learning Principles Abstract 2.1. Environmental Constraints Exercises 2.2. Statistical Learning Exercises 2.3. Information-Based Learning Exercises 2.4. Learning Under the Parsimony Principle 2.5. Scholia Bibliography Chapter 3: Linear Threshold Machines Abstract 3.1. Linear Machines Exercises 3.2. Linear Machines With Threshold Units Exercises 3.3. Statistical View Exercises 3.4. Algorithmic Issues Exercises 3.5. Scholia Bibliography Chapter 4: Kernel Machines Abstract 4.1. Feature Space Exercises 4.2. Maximum Margin Problem Exercises 4.3. Kernel Functions Exercises 4.4. Regularization Exercises 4.5. Scholia Bibliography Chapter 5: Deep Architectures Abstract 5.1. Architectural Issues Exercises 5.2. Realization of Boolean Functions Exercises 5.3. Realization of Real-Valued Functions Exercises 5.4. Convolutional Networks Exercises 5.5. Learning in Feedforward Networks Exercises 5.6. Complexity Issues Exercises 5.7. Scholia Bibliography Chapter 6: Learning and Reasoning With Constraints Abstract 6.1. Constraint Machines Exercises 6.2. Logic Constraints in the Environment Exercises 6.3. Diffusion Machines Exercises 6.4. Algorithmic Issues Exercises 6.5. Life-Long Learning Agents Exercises 6.6. Scholia Bibliography Chapter 7: Epilogue Abstract Bibliography Chapter 8: Answers to Exercises Section 1.1 Section 1.2 Section 1.3 Section 2.1 Section 2.2 Section 3.1 Section 3.2 Section 3.3 Section 3.4 Section 4.1 Section 4.2 Section 4.3 Section 4.4 Section 5.1 Section 5.2 Section 5.3 Section 5.4 Section 5.5 Section 5.7 Section 6.1 Section 6.2 Section 6.3 Section 6.4 Bibliography Appendix A: Constrained Optimization in Finite Dimensions Appendix B: Regularization Operators Appendix C: Calculus of Variations C.1. Functionals and Variations C.2. Basic Notion on Variations C.3. Euler–Lagrange Equations C.4. Variational Problems With Subsidiary Conditions Appendix D: Index to Notation Bibliography Index
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.