This book focuses on various techniques of computational intelligence, both single ones and those which form hybrid methods. Those techniques are today commonly applied issues of artificial intelligence, e.g. to process speech and natural language, build expert systems and robots. The first part of the book presents methods of knowledge representation using different techniques, namely the rough sets, type-1 fuzzy sets and type-2 fuzzy sets. Next various neural network architectures are presented and their learning algorithms are derived. Moreover, the family of evolutionary algorithms is discussed, in particular the classical genetic algorithm, evolutionary strategies and genetic programming, including connections between these techniques and neural networks and fuzzysystems. In the last part of the book, various methods of data partitioning and algorithms of automatic data clustering are given and new neuro-fuzzy architectures are studied and compared. Self-contained, easy accessible and comprehensive textbook for graduate students and researchers in computational intelligence. Well-organized modern approach to methods and techniques of intelligentcalculations including examples and exercises in each chapter. Includes a preface by Jacek Zurada, president of IEEE Computational Intelligence Society INDICE: Introduction.- Selected issues of artificial intelligence.- Methods of knowledge representation using rough sets.- Methods of knowledge representation using type-1 fuzzy sets.- Methods of knowledge representation using type-2 fuzzy sets.- Neural networks and their learning algorithms.- Evolutionary algorithms.- Data clustering methods.- Neuro-fuzzy systems of Mamdani, logicaland Takagi-Sugeno type.- Flexible neuro-fuzzy systems.
- ISBN: 978-3-540-76287-4
- Editorial: Springer
- Encuadernacion: Cartoné
- Páginas: 525
- Fecha Publicación: 01/03/2008
- Nº Volúmenes: 1
- Idioma: Inglés