Description
This revision continues to provide a balanced perspective on the language schools, theories, and applications of artificial intelligence (AI). George Luger unifies the diverse branches of AI through a detailed discussion of its theoretical foundations. The book presents case-based reasoning, genetic algorithms, neural nets, agents, and stochastic models of natural language understanding, as well as coverage of emergent computation and artificial life. Part I introduces AI concepts; Part II discuss the research tools for AI problem solving; Part III demonstrates representations for AI and knowledge-sensitive problem solving; Part IV offers an extensive presentation of issues in machine learning; Part V continues the presentation of important AI application areas; and Part VI presents Lisp and Prolog.
Features
- NEW! Reflects the growing importance of agent-based problem solving as an approach to AI technology.
- Provides a balanced perspective on the language schools, theories, and applications of AI, and has been updated to reflect the growing importance of agent-based problem solving as an approach to AI technology.
Table Of Contents
I. ARTIFICIAL INTELLIGENCE: ITS ROOTS AND SCOPE.
1. AI: History and Applications.
From Eden to ENIAC: Attitudes toward intelligence, knowledge and human artifice.
Overview of AI application areas.
Artificial intelligence-a summary.
Epilogue and references.
Exercises.
II. ARTIFICIAL INTELLIGENCE AS REPRESENTATION AND SEARCH.
2. The Predicate Calculus.
Introduction.
The propositional calculus.
The predicate calculus.
Using inference rules to produce predicate calculus expressions.
Application: a logic-based financial advisor.
Epilogue and references.
Exercises.
Introduction.
Graph theory.
Strategies for state space search.
Using the state space to represent reasoning with the predicate calculus.
Epilogue and references.
Exercises.
Introduction.
An algorithm for heuristic search.
Admissibility, monotonicity, and informedness.
Using heuristics in games.
Complexity issues.
Epilogue and references.
Exercises.
Introduction.
Recursion-based search.
Pattern-directed search.
Production systems.
The blackboard architecture for problem solving.
Epilogue and references.
Exercises.
III. REPRESENTATION AND INTELLIGENCE: THE AI CHALLENGE.
6 .Knowledge Representation. Issues in knowledge representation.
A brief history of AI representational systems.
Conceptual graphs: a network language.
Alternatives to explicit representation.
Agent based and distributed problem solving.
Epilogue and references.
Exercises.
Introduction.
Overview of expert systems technology.
Rule-based expert systems.
Model-based, case based, and hybrid systems.
Planning.
Epilogue and references.
Exercises.
8. Reasoning in Uncertain Situations. Introduction.
Logic-based abductive inference.
Abduction: alternatives to logic.
The stochastic approach to uncertainty.
Epilogue and references.
Exercises.
IV. MACHINE LEARNING.
9. Machine Learning: Symbol-Based. Introduction.
A framework for symbol-based learning.
Version space search.
The ID3 decision tree induction algorithm.
Inductive bias and learnability.
Knowledge and learning.
Unsupervised learning.
Reinforcement learning.
Epilogue and references.
Exercises.
Introduction.
Foundations for connectionist networks.
Perceptron learning.
Backpropagation learning.
Competitive learning.
Hebbian coincidence learning.
Attractor networks or "Memories."
Epilogue and references.
Exercises.
Social and emergent models of learning.
The genetic algorithm.
Classifier systems and genetic programming.
Artificial life and society-based learning.
Epilogue and references.
Exercises.
V. ADVANCED TOPICS FOR AI PROBLEM SOLVING.
12. Automated Reasoning. Introduction to weak methods in theorem proving.
The general problem solver and difference tables.
Resolution theorem proving.
PROLOG and automated reasoning.
Further issues in automated reasoning.
Epilogue and references.
Exercises.
Role of knowledge in language understanding.
Deconstructing language: a symbolic analysis.
Syntax.
Syntax and knowledge with ATN parsers.
Stochastic tools for language analysis.
Natural language applications.
Epilogue and references.
Exercises.
VI. LANGUAGES AND PROGRAMMING TECHNIQUES FOR ARTIFICIAL INTELLIGENCE.
14. An Introduction to PROLOG. Introduction.
Syntax for predicate calculus programming.
Abstract data types (ADTs) in PROLOG.
A production system example in PROLOG.
Designing alternative search strategies.
A PROLOG planner.
PROLOG: meta-predicates, types, and unification.
Meta-interpreters in PROLOG.
Learning algorithms in PROLOG.
Natural language processing in PROLOG.
Epilogue and references.
Exercises.
Introduction.
LISP: a brief overview.
Search in LISP: a functional approach to the farmer, wolf, goat, and cabbage problem.
Higher-order functions and procedural abstraction.
Search strategies in LISP.
Pattern matching in LISP.
A recursive unification function.
Interpreters and embedded languages.
Logic programming in LISP.
Streams and delayed evaluation.
An expert system shell in LISP.
Semantic networks and inheritance in LISP.
Object-oriented programming using CLOS.
Learning in LISP: the ID3 algorithm.
Epilogue and references.
Exercises.
VII. EPILOGUE.
16. Artificial Intelligence as Empirical Enquiry. Introduction.
Artificial intelligence: a revised definition.
The science of intelligent systems.
AI: current issues and future directions.
Epilogue and references.
