This is a comprehensive overview of the basics of fuzzy control, which also brings together some recent research results in soft computing, in particular fuzzy logic using genetic algorithms and neural networks.

This book offers researchers not only a solid background but also a snapshot of the current state of the art in this field.

This book deals with combinatorial aspects of epistasis, a notion that existed for years in genetics and appeared in the ?eld of evolutionary algorithms in the early 1990s. Even thoughthe?rst chapterputsepistasisintheperspective ofevolutionary algorithms and arti?cial intelligence, and applications occasionally pop up in other chapters, thisbookisessentiallyaboutmathematics, aboutcombinatorialtechniques to compute in an e?cient and mathematically elegant way what will be de?ned as normalized epistasis. Some of the material in this book ?nds its origin in the PhD theses of Hugo Van Hove [97] and Dominique Suys [95]. The sixth chapter also contains material that appeared in the dissertation of Luk Schoofs [84]. Together with that of M. Teresa Iglesias [36], these dissertations form the backbone of a decade of mathematical ventures in the world of epistasis. The authors wish to acknowledge support from the Flemish Fund of Scienti?c - search (FWO-Vlaanderen) and of the Xunta de Galicia. They also wish to explicitly mentiontheintellectualandmoralsupporttheyreceivedthroughoutthepreparation of this work from their family and their colleagues Emilio Villanueva, Jose Mar'a Barja and Arnold Beckelheimer, as well as our local T T Xpert Jan Adriaenssens.

Just suppose, for a moment, that all rings of integers in algebraic number fields were unique factorization domains, then it would be fairly easy to produce a proof of Fermat's Last Theorem, fitting, say, in the margin of this page. Unfortunately however, rings of integers are not that nice in general, so that, for centuries, math ematicians had to search for alternative proofs, a quest which culminated finally in Wiles' marvelous results - but this is history. The fact remains that modern algebraic number theory really started off with in vestigating the problem which rings of integers actually are unique factorization domains. The best approach to this question is, of course, through the general the ory of Dedekind rings, using the full power of their class group, whose vanishing is, by its very definition, equivalent to the unique factorization property. Using the fact that a Dedekind ring is essentially just a one-dimensional global version of discrete valuation rings, one easily verifies that the class group of a Dedekind ring coincides with its Picard group, thus making it into a nice, functorial invariant, which may be studied and calculated through algebraic, geometric and co homological methods. In view of the success of the use of the class group within the framework of Dedekind rings, one may wonder whether it may be applied in other contexts as well. However, for more general rings, even the definition of the class group itself causes problems."

The already broad range of applications of ring theory has been enhanced in the eighties by the increasing interest in algebraic structures of considerable complexity, the so-called class of quantum groups. One of the fundamental properties of quantum groups is that they are modelled by associative coordinate rings possessing a canonical basis, which allows for the use of algorithmic structures based on Groebner bases to study them. This book develops these methods in a self-contained way, concentrating on an in-depth study of the notion of a vast class of non-commutative rings (encompassing most quantum groups), the so-called Poincar -Birkhoff-Witt rings. We include algorithms which treat essential aspects like ideals and (bi)modules, the calculation of homological dimension and of the Gelfand-Kirillov dimension, the Hilbert-Samuel polynomial, primality tests for prime ideals, etc.

Solving pattern recognition problems involves an enormous amount of computational effort. By applying genetic algorithms - a computational method based on the way chromosomes in DNA recombine - these problems are more efficiently and more accurately solved. Genetic Algorithms for Pattern Recognition covers a broad range of applications in science and technology, describing the integration of genetic algorithms in pattern recognition and machine learning problems to build intelligent recognition systems. The articles, written by leading experts from around the world, accomplish several objectives: they provide insight into the theory of genetic algorithms; they develop pattern recognition theory in light of genetic algorithms; and they illustrate applications in artificial neural networks and fuzzy logic. The cross-sectional view of current research presented in Genetic Algorithms for Pattern Recognition makes it a unique text, ideal for graduate students and researchers.

Solving pattern recognition problems involves an enormous amount of computational effort. By applying genetic algorithms - a computational method based on the way chromosomes in DNA recombine - these problems are more efficiently and more accurately solved. Genetic Algorithms for Pattern Recognition covers a broad range of applications in science and technology, describing the integration of genetic algorithms in pattern recognition and machine learning problems to build intelligent recognition systems. The articles, written by leading experts from around the world, accomplish several objectives: they provide insight into the theory of genetic algorithms; they develop pattern recognition theory in light of genetic algorithms; and they illustrate applications in artificial neural networks and fuzzy logic. The cross-sectional view of current research presented in Genetic Algorithms for Pattern Recognition makes it a unique text, ideal for graduate students and researchers.

Just suppose, for a moment, that all rings of integers in algebraic number fields were unique factorization domains, then it would be fairly easy to produce a proof of Fermat's Last Theorem, fitting, say, in the margin of this page. Unfortunately however, rings of integers are not that nice in general, so that, for centuries, math ematicians had to search for alternative proofs, a quest which culminated finally in Wiles' marvelous results - but this is history. The fact remains that modern algebraic number theory really started off with in vestigating the problem which rings of integers actually are unique factorization domains. The best approach to this question is, of course, through the general the ory of Dedekind rings, using the full power of their class group, whose vanishing is, by its very definition, equivalent to the unique factorization property. Using the fact that a Dedekind ring is essentially just a one-dimensional global version of discrete valuation rings, one easily verifies that the class group of a Dedekind ring coincides with its Picard group, thus making it into a nice, functorial invariant, which may be studied and calculated through algebraic, geometric and co homological methods. In view of the success of the use of the class group within the framework of Dedekind rings, one may wonder whether it may be applied in other contexts as well. However, for more general rings, even the definition of the class group itself causes problems."

The already broad range of applications of ring theory has been enhanced in the eighties by the increasing interest in algebraic structures of considerable complexity, the so-called class of quantum groups. One of the fundamental properties of quantum groups is that they are modelled by associative coordinate rings possessing a canonical basis, which allows for the use of algorithmic structures based on Groebner bases to study them. This book develops these methods in a self-contained way, concentrating on an in-depth study of the notion of a vast class of non-commutative rings (encompassing most quantum groups), the so-called Poincar -Birkhoff-Witt rings. We include algorithms which treat essential aspects like ideals and (bi)modules, the calculation of homological dimension and of the Gelfand-Kirillov dimension, the Hilbert-Samuel polynomial, primality tests for prime ideals, etc.

This is a comprehensive overview of the basics of fuzzy control, which also brings together some recent research results in soft computing, in particular fuzzy logic using genetic algorithms and neural networks.

This book offers researchers not only a solid background but also a snapshot of the current state of the art in this field.

This book deals with combinatorial aspects of epistasis, a notion that existed for years in genetics and appeared in the ?eld of evolutionary algorithms in the early 1990s. Even thoughthe?rst chapterputsepistasisintheperspective ofevolutionary algorithms and arti?cial intelligence, and applications occasionally pop up in other chapters, thisbookisessentiallyaboutmathematics, aboutcombinatorialtechniques to compute in an e?cient and mathematically elegant way what will be de?ned as normalized epistasis. Some of the material in this book ?nds its origin in the PhD theses of Hugo Van Hove [97] and Dominique Suys [95]. The sixth chapter also contains material that appeared in the dissertation of Luk Schoofs [84]. Together with that of M. Teresa Iglesias [36], these dissertations form the backbone of a decade of mathematical ventures in the world of epistasis. The authors wish to acknowledge support from the Flemish Fund of Scienti?c - search (FWO-Vlaanderen) and of the Xunta de Galicia. They also wish to explicitly mentiontheintellectualandmoralsupporttheyreceivedthroughoutthepreparation of this work from their family and their colleagues Emilio Villanueva, Jose Mar'a Barja and Arnold Beckelheimer, as well as our local T T Xpert Jan Adriaenssens.