Artificial Intelligence

Artificial Intelligence provides information pertinent to the fundamental aspects of artificial intelligence. This book presents the basic mathematical and computational approaches to problems in the artificial intelligence field.
Organized into four parts encompassing 16 chapters, this book begins with an overview of the various fields of artificial intelligence. This text then attempts to connect artificial intelligence problems to some of the notions of computability and abstract computing devices. Other chapters consider the general notion of computability, with focus on the interaction between computability theory and artificial intelligence. This book discusses as well the concepts of pattern recognition, problem solving, and machine comprehension. The final chapter deals with the study of machine comprehension and reviews the fundamental mathematical and computing techniques underlying artificial intelligence research.
This book is a valuable resource for seniors and graduate students in any of the computer-related sciences, or in experimental psychology. Psychologists, general systems theorists, and scientists will also find this book useful.

Contenu

Preface

Acknowledgments

I Introduction

Chapter I The Scope of Artificial Intelligence

1.0 Is There Such a Thing?

1.1 Problem Solving

1.2 Pattern Recognition

1.3 Game Playing and Decision Making

1.4 Natural Language and Machine Comprehension

1.5 Self-Organizing Systems

1.6 Robotology

Chapter II Programming, Program Structure, and Computability

2.0 The Relevance of Computability

2.1 Computations on Strings

2.2 Formal Grammars

2.3 Turing Machines

2.4 Linear Bounded Automata and Type 1 Languages

2.5 Pushdown Automata and Type 2 Languages

2.6 Finite Automata and Regular (Type 3) Languages

2.7 Summary and Comments on Practicality

II Pattern Recognition

Chapter III General Considerations in Pattern Recognition

3.0 Classification

3.1 Categorizing Pattern-Recognition Problems

3.2 Historical Perspective and Current Issues

Chapter IV Pattern Classification and Recognition Methods Based on Euclidean Description Spaces

4.0 General

4.1 Bayesian Procedures in Pattern Recognition

4.2 Classic Statistical Approach to Pattern Recognition and Classification

4.3 Classification Based on Proximity of Descriptions

4.4 Learning Algorithms

4.5 Clustering

Chapter V Non-Euclidean Parallel Procedures: The Perceptron

5.0 Introduction and Historical Comment

5.1 Terminology

5.2 Basic Theorems for Order-Limited Perceptrons

5.3 Substantive Theorems for Order-Limited Perceptrons

5.4 Capabilities of Diameter-Limited Perceptrons

5.5 The Importance of Perceptron Analysis

Chapter VI Sequential Pattern Recognition

6.0 Sequential Classification

6.1 Definitions and Notation

6.2 Bayesian Decision Procedures

6.3 Bayesian Optimal Classification Procedures Based on Dynamic Programming

6.4 Approximations Based on Limited Look Ahead Algorithms

6.5 Convergence in Sequential Pattern Recognition

Chapter VII Grammatical Pattern Classification

7.0 The Linguistic Approach to Pattern Analysis

7.1 The Grammatical Inference Problem

7.2 Grammatical Analysis Applied to Two-Dimensional Images

Chapter VIII Feature Extraction

8.0 General

8.1 Formalization of the Factor-Analytic Approach

8.2 Formalization of the Binary Measurement Case

8.3 Constructive Heuristics for Feature Detection

8.4 An Experimental Study of Feature Generation in Pattern Recognition

8.5 On Being Clever

III Theorem Proving and Problem Solving

Chapter IX Computer Manipulable Representations in Problem Solving

9.0 The Use of Representations

9.1 A Typology of Representations

9.2 Combining Representations

Chapter X Graphic Representations in Problem Solving

10.0 Basic Concepts and Definitions

10.1 Algorithms for Finding a Minimal Path to a Single Goal Node

10.2 An "Optimal" Ordered Search Algorithm

10.3 Tree Graphs and Their Use

Chapter XI Heuristic Problem-Solving Programs

11.0 General Comments

11.1 Terminology

11.2 The General Problem Solver (GPS)

11.3 The Fortran Deductive System-Automatic Generation of Operator-Difference Tables

11.4 Planning

Chapter XII Theorem Proving

12.0 Theorem Proving Based on Herbrand Proof Procedures

12.1 The Resolution Principle

12.2 Simple Refinement Strategies

12.3 Ancestory Strategies

12.4 Syntactic Strategies

12.5 Semantic Strategies

12.6 Heuristics

12.7 Quantification

12.9 Problems and Future Development

IV Comprehension

Chapter XIII Computer Perception

13.0 The Problem of Perception

13.1 Vision

13.2 Perception of Speech by Computer

Chapter XIV Question Answering

14.0 The Problem

14.1 Data Structures

14.2 Deductive Inference in Information Retrieval

14.3 Comprehension without logic

Chapter XV Comprehension of Natural Language

15.0 The Problem

15.1 Natural Language: The Mathematical Model

15.2 The Psychological Model

Chapter XVI Review and Prospectus

16.0 Things Done and Undone

16.1 Some Problems of Philosophy

16.2 A General Theory of Thought

References

Author Index

Subject Index