Table of Contents

Front sections

Part One
Foundations (pg 1)

1. Intelligence (pg 3)
What Is Intelligence? (pg 3)
Theories of Intelligence (pg 4)
Theories of Mind (pg 8)
How Can Intelligence Be Measured Or Evaluated? (pg 10)
Assesing Human Intelligence (pg 10)
Assesing Machine Intelligence (pg 12)
Is Man The Only Intelligent Animal? (pg 12)
The Machinery of Intelligence
Reliance on Paradigms (pg 13)
Two Basic Paradigms (pg 13)
Artificial Intelligence (AI) (pg 15)
The Mechanization of Thought (pg 15)
The Computer and the Two Paradigms (pg 18)
How Can We Distinguish Between Mechanical and Intelligent Behavior? (pg 18)
The Role of Representation in Intelligent Behavior (pg 20)
SUMMARY AND DISCUSSION (pg 20)

2. The Brain and The Computer (pg 23)
The Human Brain (pg 24)
Evolution of the Brain (pg 24)
Architecture of the Brain (pg 30)
The Computer (pg 39)
The Nature of Computer Programs and Algorithms (pg 40)
The Universal Turing Machine (pg 43)
Limitations on the Computational Ability of a Logical Device (pg 43)
The Godel Incompleteness Theorem (pg 43)
Unsolvability by Machine (pg 45)
Implications of Godel's Theorem (pg 46)
Computational Complexity - the Existence of Solvable but Intrinsically Difficult Problems (pg 47)
Limitations on the Computational Ability of a Physical Device (pg 49)
Reliable Computation With Unreliable Components (pg 51)
DISCUSSION (pg 55)

Appendixes (pg 58)
2-1 The Nerve Cell and Nervous System Organization (pg 58)
2-2 The Digital Computer (pg 61)

3. The Representation of Knowledge (pg 63)
Representation: Concept (pg 64)
Forms vs. Content of Knowledge (pg 64)
Representing Knowledge (pg 64)
The Relation Between a Representation and Things Represented (pg 66)
Role of Representation (pg 67)
Representation Employed in Human Thinking (pg 67)
The Use of Models and Representations (pg 68)
The Use of "Visual" Representations (pg 69)
Effectiveness of a Representation (pg 69)
Representation Employed in Artificial Intellegence (pg 71)
Feature Space (or Decision Space) (pg 74)
Decision Tree/Game Tree (pg 75)
Isomorchic/Iconic/Analogical Representations (pg 77)
DISCUSSION (pg 80)

Part Two
Cognition (pg 81)

4. Reasoning and Problem Solving (pg 83)
Human Reasoning (pg 84)
Human Logical Reasoning (pg 85)
Human Probabilistic Reasoning (pg 86)
Formal Reasoning and Problem Solving (pg 87)
Requirements for a Problem Solver (pg 87)
Categories of Reasoning (pg 88)
The Deductive Logic Formalism (pg 90)
Propositional Calculus (pg 90)
Propositional Resolution (pg 91)
Predicates (pg 93)
Quantifiers (pg 93)
Semantics (pg 93)
Computational Issues (pg 94)
Nonstandard Logics (pg 95)
Inductive Reasoning
Measures of Belief (pg 97)
Bayesian Reasoning (pg 98)
Belief Functions (pg 100)
Representing a Problem in a Probabilistic Formalism (pg 103)
Comments concerning the Probabilistic Formalism (pg 103 )
Additional Formalisms for Reasoning (pg 106)
Algebraic/Mathematical Systems (pg 106)
Heuristic Search (pg 106)
Programming Systems That Facilitate Reasoning and Problem Solving (pg 108)
Common-Sense Reasoning (pg 109)
Problem Solving and Theorem Proving (pg 110)
Representing the Problem (pg 111)
The Predicate Calculus Representation for the Monkey/Banana (M/B) Problem (pg 112)
PROLOG Representation of the M/B Problem (pg 113)
Production Rule (OPS-5) Representation for the M/B Problem (pg 113)
General Problem Solver Representation for the M/B Problem (pg 114)
Formalisms or Reasoning Systems? (pg 115)
Relating Reasoning Formalisms to the Real World (pg 115)
DISCUSSION (pg 116)

Appendixes (pg 117)
4-1 AI programming Languages (pg 117)
4-2 The Monkey/Bananas Problem (pg 122)

5. Learning (pg 129)
Human and Animal Learning (pg 130)
Types of Animal Learning (pg 131)
Piaget's Theory of Human Intellectual Development (pg 132)
Similarity (pg 135)
Similarity Based on Exact Match (pg 136)
Similarity Based on Approximate Match (pg 137)
Learning (pg 137)
Model Instantiation: Parameter Learning (pg 138)
Model Construction: Description Models (pg 143)
Concept Learning (pg 148)
DISCUSSION (pg 151)

Appendix (pg 152)
5-1 Parameter Learning for an Implicit Model (pg 152)

6. Language and Communication (pg 157)
Language in Animals and Man (pg 158)
Brain Structures Associated with Language Production and Understanding (pg 159)
Human Acquisition of Language (pg 161)
Animal Aquisition of Language (pg 164)
Language and Thought (pg 165)
Communication (pg 167)
The Mechanics of Communication (pg 167)
Vocabulary of Communication (pg 168)
Understanding Language (pg 169)
Machine Understanding of Language (pg 171)
Faking Understanding (pg 171)
What Does it Mean for a Computer to Understand? (pg 171)
The Study of Language (pg 173)
DISCUSSION (pg 185)

Appendix (pg 186)
6-1 Representing Passing Algorithms (pg 186)

7. Expert/Knowledge-Based Systems (pg 189)
Human Experts (pg 190)
Production Systems (pg 191)
Control Structures Used in Production Systems (pg 192)
Production Systems in Psychological Modelling (pg 195)
Production Rule-Type Expert Systems (pg 197)
Plausible Reasoning in Expert Systems (pg 198)
Basic AI Issues (pg 200)
DISCUSSION (pg 202)

Appendix (pg 202)
7-1 PROSPECTOR Procedure for Hypothesis Updating (pg 202)

Part Three
Perception (Vision) (pg 205)

8. Vision (pg 207)
The Nature of Organic Vision (pg 207)
The Evolution and Physiology of Organic Vision (pg 209)
Seeing and the Evolution of Intelligence (pg 209)
Evolution and Physiology of the Organic Eye (pg 211)
Eye and Brain (pg 213)
The Psychology of Vision (pg 220)
Perceiving the Visual World: Recognising Patterns (pg 220)
Perceptual Organisation (pg 224)
Visual Illusions (pg 226)
Visual Thinking, Visual Memory, and Cultural Factors (pg 229)
DISCUSSIONS (pg 232)

Appendixes (pg 233)
8-1 Color Vision and Light (pg 233)
8-2 Stereo Depth Perception and the Structure of the Human Visual Cortex (pg 236)

9. Computational Vision (pg 239)
Signals-to-Symbols Paradigm (pg 241)
Low Level Scene Analysis (LLSA) (pg 242)
Image Acquisition (Scanning and Quantizing) (pg 243)
Image Preprocessing (Thresholding and Smoothing) (pg 245)
Detection of Local Discontinuities and Homogeneities (Edges, Textures, Color) (pg 248)
Local Scene Geometry from a Single Image (Shape from Shading and Texture) (pg 256)
Local Scene Geometry from Multiple Images (Stereo and Optic Flow) (pg 259)
Intermediate Level Scene Analysis (ILSA) (pg 262)
Image/Scene Partitioning (pg 264)
Edge Linking and Deriving a Line Sketch (pg 269)
Recovering Three-Dimensional Scene Geometry from a Line Drawing (pg 272)
Image Matching (pg 276)
Object Labelling (pg 278)
Model Selection and Instantiation (pg 279)
High Level Scene Analysis (HLSA) (pg 281)
Image/Scene Description (pg 281)
Knowledge Representation (pg 283)
The Problem of High-Level Scene Analysis (pg 285)
Reasoning About a Simple Scene (pg 285)
DISCUSSION (pg 286)
A Basic Concern About Signals-to-Symbols (pg 287)
Necessary Attributes of a Machine Vision System (pg 288)
Summary (pg 289)

Appendixes (pg 289)
9-1 Mathematical Techniques for Information Integration (pg 289)
9-2 A Path-Finding Algorithm (pg 297)
9-3 Relational (Rubber Sheet) Image Matching (pg 299)

Epilogue (pg 301)
Bibliography (pg 311)
Index (pg 325)

Return to front page

Valid HTML 4.01!