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.
1. Cover image - p. iv 2. Title page - p. iv 3. Table of Contents - p. iv 4. Copyright - p. iv 5. Dedication - p. v 6. Preface - p. xiii 7. Notes on the Exercises - p. xix 8. Chapter 1: The Big Picture - p. xx 9. Chapter 2: Learning Principles - p. 58 10. Chapter 3: Linear Threshold Machines - p. 121 11. Chapter 4: Kernel Machines - p. 184 12. Chapter 5: Deep Architectures - p. 235 13. Chapter 6: Learning and Reasoning With Constraints - p. 338 14. Chapter 7: Epilogue - p. 444 15. Chapter 8: Answers to Exercises - p. 450 16. Appendix A: Constrained Optimization in Finite Dimensions - p. 507 17. Appendix B: Regularization Operators - p. 510 18. Appendix C: Calculus of Variations - p. 516 19. Appendix D: Index to Notation - p. 528 20. Bibliography - p. 534 21. Index - p. 552
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.
1. Cover image - p. iv 2. Title page - p. iv 3. Table of Contents - p. iv 4. Copyright - p. iv 5. Dedication - p. v 6. Preface - p. xiii 7. Notes on the Exercises - p. xix 8. Chapter 1: The Big Picture - p. xx 9. Chapter 2: Learning Principles - p. 58 10. Chapter 3: Linear Threshold Machines - p. 121 11. Chapter 4: Kernel Machines - p. 184 12. Chapter 5: Deep Architectures - p. 235 13. Chapter 6: Learning and Reasoning With Constraints - p. 338 14. Chapter 7: Epilogue - p. 444 15. Chapter 8: Answers to Exercises - p. 450 16. Appendix A: Constrained Optimization in Finite Dimensions - p. 507 17. Appendix B: Regularization Operators - p. 510 18. Appendix C: Calculus of Variations - p. 516 19. Appendix D: Index to Notation - p. 528 20. Bibliography - p. 534 21. Index - p. 552
