Pattern Recognition and Machine Learning

Table of contents

1. Cover image
2. Title page
3. Table of Contents
4. Copyright
5. Preface
6. Study Guide
7. Chapter 1: Recognition and Learning by a Computer
   1. 1.1 What Is Recognition by a Computer?
   2. 1.2 Representation and Transformation in Recognition
   3. 1.3 What Is Learning by a Computer?
   4. 1.4 Representation and Transformation in Learning
   5. 1.5 Example of Recognition/Learning System
   6. Summary
   7. Exercises
8. Chapter 2: Representing Information
   1. 2.1 Pattern Function and Bit Pattern
   2. 2.2 The Representation of Spatial Structure
   3. 2.3 Graph Representation
   4. 2.4 Tree Representation
   5. 2.5 List Representation
   6. 2.6 Predicate Logic Representation
   7. 2.7 Horn Clause Logic Representation
   8. 2.8 Declarative Representation
   9. 2.9 Procedural Representation
   10. 2.10 Representation Using Rules
   11. 2.11 Semantic Networks and Frames
   12. 2.12 Representation Using Fourier Series
   13. 2.13 Classification of Representation Methods
   14. Summary
   15. Exercises
9. Chapter 3: Generation and Transformation of Representations
   1. 3.1 Methods of Generating and Transforming Representations
   2. 3.2 Linear Transformations of Pattern Functions
   3. 3.3 Sampling and Quantization of Pattern Functions
   4. 3.4 Transformation to Spatial Representations
   5. 3.5 Generation of Tree Representation
   6. 3.6 Search and Problem Solving
   7. 3.7 Logical Inference
   8. 3.8 Production Systems
   9. 3.9 Inference Using Frames
   10. 3.10 Constraint Representation and Relaxation
   11. 3.11 Summary
   12. Exercises
10. Chapter 4: Pattern Feature Extraction
    1. 4.1 Detecting an Edge
    2. 4.2 Detection of a Boundary Line
    3. 4.3 Extracting a Region
    4. 4.4 Texture Analysis
    5. 4.5 Detection of Movement
    6. 4.6 Representing a Boundary Line
    7. 4.7 Representing a Region
    8. 4.8 Representation of a Solid
    9. 4.9 Interpretation of Line Drawings
    10. Summary
    11. Exercises
11. Chapter 5: Pattern Understanding Methods
    1. 5.1 Pattern Understanding and Knowledge Representation
    2. 5.2 Pattern Matching and the Relaxation Method
    3. 5.3 Maximal Subgraph Isomorphism and Clique Method
    4. 5.4 Control in Pattern Understanding
    5. Summary
    6. Exercises
12. Chapter 6: Learning Concepts
    1. 6.1 Definition of a Concept
    2. 6.2 Methods for Concept Learning
    3. 6.3 Generalization of Well-Formed Formulas
    4. 6.4 Version Space
    5. 6.5 Conceptual Clustering
    6. Summary
    7. Exercises
13. Chapter 7: Learning Procedures
    1. 7.1 Learning Operators in Problem Solving
    2. 7.2 Learning Rules
    3. 7.3 Learning Programs
    4. Summary
    5. Exercises
14. Chapter 8: Learning Based on Logic
    1. 8.1 Explanation-Based Learning
    2. 8.2 Analogical Learning
    3. 8.3 Nonmonotonic Logic and Learning
    4. Summary
    5. Keywords
    6. Exercises
15. Chapter 9: Learning by Classification and Discovery
    1. 9.1 Representing Instances by a Decision Tree
    2. 9.2 An Algorithm for Generating a Decision Tree
    3. 9.3 Selecting a Test in Generating a Decision Tree
    4. 9.4 Learning from Noisy Data
    5. 9.5 Learning by Discovery
    6. 9.6 Discovery of New Concepts and Rules
    7. Summary
    8. Exercises
16. Chapter 10: Learning by Neural Networks
    1. 10.1 Representing neural networks
    2. 10.2 Back Propagation
    3. 10.3 Competitive Learning
    4. 10.4 Hopfield Networks
    5. 10.5 Boltzmann Machines
    6. 10.6 Parallel Computation in Recognition and Learning
    7. Summary
    8. Exercises
17. Appendix: Examples of Learning by Neural Networks
18. Answers
19. Bibliography
20. Index