Table of Contents
Chapter 1: Recognition and Learning by a Computer
1.1 What Is Recognition by a Computer?
1.2 Representation and Transformation in Recognition
1.3 What Is Learning by a Computer?
1.4 Representation and Transformation in Learning
1.5 Example of Recognition/Learning System
Chapter 2: Representing Information
2.1 Pattern Function and Bit Pattern
2.2 The Representation of Spatial Structure
2.6 Predicate Logic Representation
2.7 Horn Clause Logic Representation
2.8 Declarative Representation
2.10 Representation Using Rules
2.11 Semantic Networks and Frames
2.12 Representation Using Fourier Series
2.13 Classification of Representation Methods
Chapter 3: Generation and Transformation of Representations
3.1 Methods of Generating and Transforming Representations
3.2 Linear Transformations of Pattern Functions
3.3 Sampling and Quantization of Pattern Functions
3.4 Transformation to Spatial Representations
3.5 Generation of Tree Representation
3.6 Search and Problem Solving
3.10 Constraint Representation and Relaxation
Chapter 4: Pattern Feature Extraction
4.2 Detection of a Boundary Line
4.6 Representing a Boundary Line
4.9 Interpretation of Line Drawings
Chapter 5: Pattern Understanding Methods
5.1 Pattern Understanding and Knowledge Representation
5.2 Pattern Matching and the Relaxation Method
5.3 Maximal Subgraph Isomorphism and Clique Method
5.4 Control in Pattern Understanding
6.2 Methods for Concept Learning
6.3 Generalization of Well-Formed Formulas
Chapter 7: Learning Procedures
7.1 Learning Operators in Problem Solving
Chapter 8: Learning Based on Logic
8.1 Explanation-Based Learning
8.3 Nonmonotonic Logic and Learning
Chapter 9: Learning by Classification and Discovery
9.1 Representing Instances by a Decision Tree
9.2 An Algorithm for Generating a Decision Tree
9.3 Selecting a Test in Generating a Decision Tree
9.6 Discovery of New Concepts and Rules
Chapter 10: Learning by Neural Networks
10.1 Representing neural networks
10.6 Parallel Computation in Recognition and Learning