Buch, Englisch, 304 Seiten, Format (B × H): 183 mm x 260 mm, Gewicht: 767 g
Buch, Englisch, 304 Seiten, Format (B × H): 183 mm x 260 mm, Gewicht: 767 g
ISBN: 978-0-8493-2643-1
Verlag: CRC Press
Computational intelligence as a new development paradigm of intelligent systems has resulted from a synergy between neural networks, fuzzy sets, and genetic computations. This emerging area, even at its very earliest stage, has already attracted the attention of top researchers and practitioners. Computational Intelligence: An Introduction delivers a highly readable and fully systematic treatment of the fundamentals of CI, along with the clear presentation of sound and comprehensive analysis and design practices.This text pulls together much of the scattered information written about this emerging field. Most publications dealing with CI are highly specialized and concentrate narrowly on the symbiosis between NN, FS, and GAs. Computational Intelligence: An Introduction bridges the gap between all three areas and CI. This is an important text for anyone engaged in any way with genetic algorithms, fuzzy sets, neural networks, and computational intelligence.
Zielgruppe
Electrical engineersComputer scientistsOthers interested in learning about the field of computational intelligenceGraduate-level students in electrical engineering and computer science
Autoren/Hrsg.
Weitere Infos & Material
Chapter 1. PreliminariesComputational Intelligence: Its Inception and Research AgendaOrganization and ReadershipReferencesChapter 2. Neural Networks and NeurocomputingIntroductionGeneric Models of Computational NeuronsArchitectures of Neural Networks - A Basic TaxonomyLearning in Neural NetworksSelected Classes of Learning MethodsGeneralization Abilities of Neural NetworksEnhancements of Gradient-Based Learning in Neural NetworksConcluding RemarksProblemsReferencesChapter 3. Fuzzy SetsIntroductionBasic DefinitionTypes of Membership FunctionsCharacteristics of a Fuzzy SetMembership Function DeterminationFuzzy RelationsSet Theory Operations and Their PropertiesTriangular NormsTriangular Norms as the Models of Operations on Fuzzy SetsInformation-Based Characteristics of Fuzzy SetsMatching Fuzzy SetsNumerical Representation of Fuzzy SetsRough SetsRough Sets and Fuzzy SetsShadowed SetsThe Frame of CognitionProbability and Fuzzy SetsHybrid Fuzzy-Probabilistic Models of UncertaintyConclusionsProblemsReferencesChapter 4. Computations with Fuzzy SetsIntroductory RemarksThe Extension PrincipleFuzzy NumbersFuzzy Rule-Based ComputingFuzzy Controller and Fuzzy ControlRule-Based Systems with Nonmonotonic OperationsConclusionsProblemsReferencesChapter 5. Evolutionary ComputingIntroductionGradient-Based and Probabilistic Optimization as Examples of Single-Point Search TechniquesGenetic Algorithms - Fundamentals and a Basic AlgorithmSchemata Theorem - A Conceptual Backbone of GAsFrom Search Space to GA Search SpaceExploration and Exploitation of the Search SpaceExperimental StudiesClasses of Evolutionary ComputationConclusionsProblemsReferencesChapter 6. Fuzzy Neural SystemsIntroductionNeurocomputing in Fuzzy Set TechnologyFuzzy Sets in the Technology of NeurocomputingFuzzy Sets in the Preprocessing and Enhancements of Training DataUncertainty Representation in Neural NetworksNeural Calibration of Membership FunctionsKnowledge-Based Learning SchemesLinguistic Interpretation of Neural NetworksHybrid Fuzzy Neural Computing StructuresConclusionsProblemsReferencesChapter 7. Fuzzy Neural NetworksLogic-Based NeuronsLogic Neurons and Fuzzy Neural Networks with FeedbackReferential Logic-Based NeuronsLearning in Fuzzy Neural NetworksCase StudiesConclusionsProblemsReferencesChapter 8. CI SystemsIntroductionFuzzy Encoding in Evolutionary ComputingFuzzy Crossover OperationsFuzzy Metarules in Genetic ComputingRelational Structures and Their OptimizationThe Satisfiability ProblemEvolutionary Rule-Based Modeling of Analytical RelationshipsGenetic Optimization of Neural NetworksGenetic Optimization of Rule-Based SystemsConclusionsProblemsReferencesIndex