1st Edition
Artificial Intelligence and Soft Computing Behavioral and Cognitive Modeling of the Human Brain
With all the material available in the field of artificial intelligence (AI) and soft computing-texts, monographs, and journal articles-there remains a serious gap in the literature. Until now, there has been no comprehensive resource accessible to a broad audience yet containing a depth and breadth of information that enables the reader to fully understand and readily apply AI and soft computing concepts.
Artificial Intelligence and Soft Computing fills this gap. It presents both the traditional and the modern aspects of AI and soft computing in a clear, insightful, and highly comprehensive style. It provides an in-depth analysis of mathematical models and algorithms and demonstrates their applications in real world problems.
Beginning with the behavioral perspective of "human cognition," the text covers the tools and techniques required for its intelligent realization on machines. The author addresses the classical aspects-search, symbolic logic, planning, and machine learning-in detail and includes the latest research in these areas. He introduces the modern aspects of soft computing from first principles and discusses them in a manner that enables a beginner to grasp the subject. He also covers a number of other leading aspects of AI research, including nonmonotonic and spatio-temporal reasoning, knowledge acquisition, and much more.
Artificial Intelligence and Soft Computing: Behavioral and Cognitive Modeling of the Human Brain is unique for its diverse content, clear presentation, and overall completeness. It provides a practical, detailed introduction that will prove valuable to computer science practitioners and students as well as to researchers migrating to the subject from other disciplines.
Evolution of Computing
Defining AI
General Problem Solving Approaches in AI
The Disciplines of AI
A Brief History of AI
Characteristic Requirement for the Realization of Intelligent Systems
Programming Languages for AI
Architecture for AI Machines
Objective and Scope of the Book
Summary
THE PSYCHOLOGICAL PERSPECTIVE OF COGNITION
Introduction
The Cognitive Perspective of Pattern Recognition
Cognitive Models of Memory
Mental Imagery
Understanding a Problem
A Cybernetic View to Cognition
Scope of Realization of Cognition in AI
Summary
PRODUCTION SYSTEMS
Introduction
Production Rules
The Working Memory
The Control Unit / Interpreter
Conflict Resolution Strategies
An Alternative Approach for Conflict Resolution
An Illustrative Production System
The RETE Match Algorithm
Types of Production Systems
Forward versus Backward Production Systems
General Merits of a Production System
Knowledge Base Optimization in a Production System
Conclusions
PROBLEM SOLVING BY INTELLIGENT SEARCH
Introduction
General Problem Solving Approaches
Heuristic Search
Adversary Search
Conclusions
THE LOGIC OF PROPOSITIONS AND PREDICATES
Introduction
Formal Definitions
Tautologies in Propositional Logic
Theorem Proving by Propositional Logic
Resolution in Propositional Logic
Soundness and Completeness of Propositional Logic
Predicate Logic
Writing a Sentence into Clause Forms
Unification of Predicates
Robinson's Inference Rule
Different Types of Resolution
Semi-Decidability
Soundness and Completeness of Predicate Logic
Conclusions
PRINCIPLES OF LOGIC PROGRAMMING
Introduction to PROLOG Programming
Logic Programs - A Formal Definition
A Scene Interpretation Program
Illustrating Backtracking by flow of Satisfaction Diagrams
The SLD Resolution
Controlling Backtracking by CUT
The NOT Predicate
Negation as a Failure in Extended Logic Programs
Fixed Points in Non-Horn Clause Based Programs
Constraint Logic Programming
Conclusions
DEFAULT AND NON-MONOTONIC REASONING
Introduction
Monotonic versus Non-Monotonic Logic
Non-Monotonic Resoning Using NML-I
Fixed Points in Non-Monotonic Reasoning
Non-Monotonic Resoning Using NML-II
Truth Maintenance System
Default Reasoning
The Closed World Assumption
Circumscription
Auto-Epistemic Logic
Conclusions
STRUCTURED APPROACH TO KNOWLEDGE REPRESENTATION
Introduction
Semantic Nets
Inheritance in Semantic Nets
Manipulating Monotonic and Default Inheritance in Semantic Nets
Defeasible Reasoning in Semantic Nets
Frames
Inheritance in Tangled Frames
Petri nets
Conceptual Dependency
Scripts
Conclusions
DEALING WITH IMPRECISION AND UNCERTAINTY
Introduction
Probabilistic Reasoning
Certainty Factor Based Reasoning
Fuzzy Reasoning
Comparison of the Proposed Models
STRUCTURED APPROACH TO FUZZY REASONING
Introduction
Structural Model of Fuzzy FPN and Reachability Analysis
Behavioral Model of FPN and Stability Analysis
Forward Reasoning in FPN
Backward Reasoning in FPN
Bi-directional IFF Type Reasoning and Reciprocity
Fuzzy Modus Tollens and Duality
Non-Monotonic Reasoning in an FPN
Conclusions
REASONING WITH SPACE AND TIME
Introduction
Spatial Reasoning
Spatial Relationships among Components of an Object
Fuzzy Spatial Relationships among Objects
Temporal Reasoning by Situation Calculus
Propositional Temporal Logic
Interval Temporal Logic
Reasoning with Both Space and Time
Conclusions
INTELLIGENT PLANNING
Introduction
Planning with If-Add-Delete Operators
Least Commitment Planning
Hierarchical Task Network Planning
Multi-agent Planning
The Flowshop Scheduling Problem
Summary
MACHINE LEARNING TECHNIQUES
Introduction
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Learning by Inductive Logic Programming
Computational Learning Theory
Summary
MACHINE LEARNING USING NEURAL NETS
Biological Neural Nets
Artificial Neural Nets
Topology of Artificial Neural Nets
Learning Using Neural Nets
The Back-Propagation Training Algorithm
Widrow-Hoff's Multi-Layers ADALINE Models
Hopfield Neural Net
Associative Memory
Fuzzy Neural Nets
Self-Organizing Neural Net
Adaptive Resonance Theory (ART)
Applications of Artificial Neural Nets
GENETIC ALGORITHMS
Introduction
Deterministic Explanation of Holland's Observation
Stochastic Explanation of GA
The Markov Model for Convergence Analysis
Application of GA in Optimization Problems
Application of GA in Machine Learning
Applications of GA in Intelligent Search
Genetic Programming
Conclusions
REALIZING COGNITION USING FUZZY NEURAL NETS
Cognitive Maps
Learning by a Cognitive Map
The Recall in a Cognitive Map
Stability Analysis
Cognitive Learning with FPN
Applications in Autopilots
Generation of Control Commands by a Cognitive Map
Task Planning and Coordination
Putting it all Together
Conclusions and Future Directions
VISUAL PERCEPTION
Introduction
Low level Vision
Medium Level Vision
High Level Vision
Conclusions
LINGUISTIC PERCEPTION
Introduction
Syntactic Analysis
Augmented Transition Network Parsers
Semantic Interpretation by Case Grammar and Type Hierarchy
Discourse and Pragmatic Analysis
Applications of Natural Language Understanding
PROBLEM SOLVING BY CONSTRAINT SATISFACTION
Introduction
Formal Definitions
Constraint Propagation in Networks
Determining Satisfiability of CSP
Constraint Logic Programming
Geometric Constraint Satisfaction
Conclusions
ACQUISITION OF KNOWLEDGE
Introduction
Manual Approach for Knowledge Acquisition
Knowledge Fusion from Multiple Experts
Machine Learning Approach for Knowledge Acquisition
Knowledge Refinement by Hebbian Learning
Conclusions
VALIDATION, VERIFICATION AND MAINTENANCE ISSUES
Introduction
Valildation of Expert Systems
Verification of Knowledge Based System
Maintenance of Knowledge Based Systems
Conclusions
PARALLEL AND DISTRIBUTED ARCHITECTURE FOR INTELLIGENT SYSTEMS
Introduction
Salient Features of AI Machines
Parallelism in Heuristic Search
Parallelism at Knowledge Representational Level
Parallel Architecture for Logic Programming
Conclusions
CASE STUDY I: BUILDING A SYSTEM FOR CRIMINAL INVESTIGATION
An Overview of the Proposed Scheme
Introduction to Image Matching
Fingerprint Classification and Matching
Identification of the Suspects from Voice
Identification of the Suspects from Incidental Descriptions
Conclusions
CASE STUDY II: REALIZATION OF COGNITION FOR MOBILE ROBOTS
Mobile Robots
Scope of Realization of Cognition on Mobile Robots
Knowing the Robot's World
Types of Navigational Planning Problems
Offline Planning by Generalized Voronoi Diagram (GVD)
Path Traversal Optimization Problem
Self-Orgainizing Map (SOM)
Online Navigation by Modular Back-Propagation Neural Nets
Coordination among Sub-Modules in a Mobile Robot
An Application in a Soccer Playing Robot
The Expectations from the Readers
APPENDIX A: How to Run the Sample Programs?
APPENDIX B: Derivation of the Back-propagation Algorithm
APPENDIX C: Proof of the Theorems of Chapter 10
INDEX
Biography
Amit Konar (Jadavpur University, Calcutta, India)
