Table of Contents

Part 1 The faculty of knowledge engineering and problem solving: introduction to AI paradigms; heuristic problem solving - genetic algorithms; why expert systems, fuzzy systems, neural networks and hybrid systems for knowledge engineering and problem solving?; generic and specific AI problems - pattern recognition and classification; speech and language processing; prediction; planning, monitoring, diagnosis and control; optimization, decision making and games playing; a general approach to knowledge engineering; problems and exercises. Part 2 Knowledge engineering and symbolic artificial intelligence: data, information and knowledge - major issues in knowledge engineering; data analysis, data representation and data transformation; information structures and knowledge representation; methods for symbol manipulation and inference - inference as matching, inference as a search; propositional logic; predicate logic - PROLOG; production systems; expert systems; uncertainties in knowledge-based systems - probabilistic methods; nonprobabilistic methods for dealing with uncertainties; machine-learning methods for knowledge engineering; problems and exercises. Part 3 Neural networks for knowledge engineering and problem solving: neural networks as a problem-solving paradigm; connectionist expert systems; connectionist models for knowledge acquisition - one rule is worth a thousand data examples; symbolic rules insertion in neural networks - connectionist production systems; connectionist systems for pattern recognition and classification - image processing; connectionist systems for speech processing; connectionist systems for prediction; connectionist systems for monitoring, control, diagnosis and planning; connectionist systems for optimization and decision making; connectionist systems for modelling strategic games; problems. Part 4 Hybrid symbolic, fuzzy and connectionist systems - toward comprehensive artificial intelligence: the hybrid systems paradigm; hybrid connectionist production systems; hybrid connectionist logic programming systems; hybrid fuzzy connectionist production systems; ("pure") connectionist production systems - the NPS architecture (optional); hybrid systems for speech and language processing; hybrid systems for decision making; problems. Part 5 Neural networks, fuzzy systems and nonlinear dynamical systems chaos - toward new connectionist and fuzzy logic models: chaos; fuzzy systems and chaos - new developments in fuzzy systems; neural networks and chaos - new developments in neural networks.

Reviews

"Covering the latest issues and achievements, this well documented, precisely presented text is timely and suitable for graduate and upper undergraduate students in knowledge engineering, intelligent systems, AI, neural networks, fuzzy systems, and related areas. The author's goal is to explain the principles of neural networks and fuzzy systems and to demonstrate how they can be applied to building knowledge-based systems for problem solving. Especially useful are the comparisons between different techniques (AI rule-based methods, fuzzy methods, connectionist methods, hybrid systems) used to solve the same or similar problems."--Anca Ralescu, Associate Professor of Computer Science, University of Cincinnati

& quot; Covering the latest issues and achievements, this well documented, precisely presented text is timely and suitable for graduate and upper undergraduate students in knowledge engineering, intelligent systems, AI, neural networks, fuzzy systems, and related areas. The author's goal is to explain the principles of neural networks and fuzzy systems and to demonstrate how they can be applied to building knowledge-based systems for problem solving. Especially useful are the comparisons between different techniques (AI rule-based methods, fuzzy methods, connectionist methods, hybrid systems) used to solve the same or similar problems.& quot; -- Anca Ralescu, Associate Professor of Computer Science, University of Cincinnati

" Covering the latest issues and achievements, this well documented, precisely presented text is timely and suitable for graduate and upper undergraduate students in knowledge engineering, intelligent systems, AI, neural networks, fuzzy systems, and related areas. The author's goal is to explain the principles of neural networks and fuzzy systems and to demonstrate how they can be applied to building knowledge-based systems for problem solving. Especially useful are the comparisons between different techniques (AI rule-based methods, fuzzy methods, connectionist methods, hybrid systems) used to solve the same or similar problems." -- Anca Ralescu, Associate Professor of Computer Science, University of Cincinnati

-- Anca Ralescu, Associate Professor of Computer Science, University of Cincinnati