计算智能：Computational Intelligence: Concepts to Implementations

图书标准信息

• 作者 埃伯哈特（Russell C.Eberhart）、史玉回（Yuhui Shi） 著
• 出版社 人民邮电出版社
• 出版时间 2009-02
• 版次 1
• ISBN 9787115194039
• 定价 69.00元
• 装帧 平装
• 开本 16开
• 纸张 胶版纸
• 页数 467页
• 字数 586千字
• 正文语种 英语
• 丛书 图灵原版计算机科学系列

【内容简介】

《计算智能：从概念到实现(英文版)》面向智能系统学科的前沿领域，系统地讨论了计算智能的理论、技术及其应用，比较全面地反映了计算智能研究和应用的最新进展。书中涵盖了模糊控制、神经网络控制、进化计算以及其他一些技术及应用的内容。《计算智能：从概念到实现(英文版)》提供了大量的实用案例，重点强调实际的应用和计算工具，这些对于计算智能领域的进一步发展是非常有意义的。《计算智能：从概念到实现(英文版)》取材新颖，内容深入浅出，材料丰富，理论密切结合实际，具有较高的学术水平和参考价值。
《计算智能：从概念到实现(英文版)》可作为高等院校相关专业高年级本科生或研究生的教材及参考用书，也可供从事智能科学、自动控制、系统科学、计算机科学、应用数学等领域研究的教师和科研人员参考。

【作者简介】

RussellC.Eberhart，普度大学电子与计算机工程系主任，IEEE会士。与JamesKennedy共同提出了粒子群优化算法。曾任IEEE神经网络委员会的主席。除了本书之外。他还著有《群体智能》（影印版由人民邮电出版社出版）等。
YuhuiShi（史玉回），国际计算智能领域专家，现任JournalofSwarmIntelligence编委，IEEECIS群体智能任务组主席，西交利物浦大学电子与电气工程系教授。1992年获东南大学博士学位，先后在美国、韩国、澳大利亚等地从事研究工作，曾任美国电子资讯系统公司专家长达9年。他还是《群体智能》一书的作者之一。

【目录】

chapteroneFoundations
Definitions
BiologicalBasisforNeuralNetworks
Neurons
BiologicalversusArtificialNeuralNetworks
BiologicalBasisforEvolutionaryComputation
Chromosomes
BiologicalversusArtificialChromosomes
BehavioralMotivationsforFuzzyLogic
MythsaboutComputationalIntelligence
ComputationalIntelligenceApplicationAreas
NeuralNetworks
EvolutionaryComputation
FuzzyLogic
Summary
Exercises

chaptertwoComputationalIntelligence
Adaptation
AdaptationversusLearning
ThreeTypesofAdaptation
ThreeSpacesofAdaptation
Self-organizationandEvolution
EvolutionbeyondDarwin
HistoricalViewsofComputationalIntelligence
ComputationalIntelligenceasAdaptationandSelf-organization
TheAbilitytoGeneralize
ComputationalIntelligenceandSoftComputingversusArtificialIntelligenceandHardComputing
Summary
Exercises

chapterthreeEvolutionaryComputationConceptsandParadigms
HistoryofEvolutionaryComputation
GeneticAlgorithms
EvolutionaryProgramming
EvolutionStrategies
GeneticProgramming
ParticleSwarmOptimization
TowardUnification
EvolutionaryComputationOverview
ECParadigmAttributes
Implementation
GeneticAlgorithms
OverviewofGeneticAlgorithms
ASampleGAProblem
ReviewofGAOperationsintheSimpleExample
SchemataandtheSchemaTheorem
CommentsonGeneticAlgorithms
EvolutionaryProgramming
EvolutionaryProgrammingProcedure
FiniteStateMachineEvolutionforPrediction
FunctionOptimization
CommentsonEvolutionaryProgramming
EvolutionStrategies
Selection
KeyIssuesinEvolutionStrategies
GeneticProgramming
ParticleSwarmOptimization
Developments
Resources
Summary
Exercises

chapterfourEvolutionaryComputationImplementations
ImplementationIssues
HomogeneousversusHeterogeneousRepresentation
PopulationAdaptationversusIndividualAdaptation
StaticversusDynamicAdaptation
FlowchartsversusFiniteStateMachines
HandlingMultipleSimilarCases
AllocatingandFreeingMemorySpace
ErrorChecking
GeneticAlgorithmImplementation
ProgrammingGeneticAlgorithms
RunningtheGAImplementation
ParticleSwarmOptimizationImplementation
ProgrammingthePSOImplementation
ProgrammingtheCo-evolutionaryPSO
RunningthePSOImplementation
Summary
Exercises

chapterfiveNeuralNetworkConceptsandParadigms
NeuralNetworkHistory
WhereDidNeuralNetworksGetTheirName?
TheAgeofCamelot
TheDarkAge
TheRenaissance
TheAgeofNeoconnectionism
TheAgeofComputationalIntelligence
WhatNeuralNetworksAreandWhyTheyAreUseful
NeuralNetworkComponentsandTerminology
Terminology
InputandOutputPatterns
NetworkWeights
ProcessingElements
ProcessingElementActivationFunctions
NeuralNetworkTopologies
Terminology
Two-layerNetworks
MultilayerNetworks
NeuralNetworkAdaptation
Terminology
HebbianAdaptation
CompetitiveAdaptation
MultilayerErrorCorrectionAdaptation
SummaryofAdaptationProcedures
ComparingNeuralNetworksandOtherInformationProcessingMethods
StochasticApproximation
KalmanFilters
LinearandNonlinearRegression
Correlation
BayesClassification
VectorQuantization
RadialBasisFunctions
ComputationalIntelligence
Preprocessing
SelectingTraining，Test，andValidationDatasets
PreparingData
Postprocessing
DenormalizationofOutputData
Summary
Exercises

chaptersixNeuralNetworkImplementations
ImplementationIssues
Topology
Back-propagationNetworkInitializationandNormalization
LearningVectorQuantizerNetworkInitializationandNormalization
FeedforwardCalculationsfortheBack-propagationNetwork
FeedforwardCalculationsfortheLVQ-INet
Back-propagationSupervisedAdaptationbyErrorBack-propagation
LVQUnsupervisedAdaptationCalculations
TheLVQSupervisedAdaptationAlgorithm
IssuesinEvolvingNeuralNetworks
AdvantagesandDisadvantagesofPreviousEvolutionaryApproaches
EvolvingNeuralNetworkswithParticleSwarmOptimization
Back-propagationImplementation
ProgrammingaBack-propagationNeuralNetwork
RunningtheBack-propagationImplementation
TheKohonenNetworkImplementations
ProgrammingtheLearningVectorQuantizer
RunningtheLVQImplementation
ProgrammingtheSelf-organizingFeatureMap
RunningtheSOFMImplementation
EvolutionaryBack-propagationNetworkImplementation
ProgrammingtheEvolutionaryBack-propagationNetwork
RunningtheEvolutionaryBack-propagationNetwork
Summary
Exercises

chaptersevenFuzzySystemsConceptsandParadigms
History
FuzzySetsandFuzzyLogic
Logic，FuzzyandOtherwise
FuzzinessIsNotProbability
TheTheoryofFuzzySets
FuzzySetMembershipFunctions
LinguisticVariables
LinguisticHedges
ApproximateReasoning
ParadoxesinFuzzyLogic
EqualityofFuzzySets
Containment
NOT：TheComplementofaFuzzySet
AND：TheIntersectionofFuzzySets
OR：TheUnionofFuzzySets
CompensatoryOperators
FuzzyRules
Fuzzification
FuzzyRulesFireinParallel
Defuzzification
OtherDefuzzificationMethods
MeasuresofFuzziness
DevelopingaFuzzyController
WhyFuzzyControl
AFuzzyController
BuildingaMamdani-typeFuzzyController
FuzzyControllerOperation
Takagi-Sugeno-KangMethod
Summary
Exercises

chaptereightFuzzySystemsImplementations
ImplementationIssues
FuzzyRuleRepresentation
EvolutionaryDesignofaFuzzyRuleSystem
AnObject-orientedLanguage：C++
FuzzyRuleSystemImplementation
ProgrammingFuzzyRuleSystems
RunningtheFuzzyRuleSystem
IrisDatasetApplication
EvolvingFuzzyRuleSystems
ProgrammingtheEvolutionaryFuzzyRuleSystem
RunningtheEvolutionaryFuzzyRuleSystem
Summary
Exercises

chapternineComputationalIntelligenceImplementations
ImplementationIssues
AdaptationofGeneticAlgorithms
FuzzyAdaptation
KnowledgeElicitation
FuzzyEvolutionaryFuzzyRuleSystemImplementation
ProgrammingtheFuzzyEvolutionaryFuzzyRuleSystem
RunningtheFuzzyEvolutionaryFuzzyRuleSystem
ChoosingtheBestTools
StrengthsandWeaknesses
ModelingandOptimization
PracticalIssues
ApplyingComputationalIntelligencetoDataMining
AnExampleDataMiningSystem
Summary
Exercises

chaptertenPerformanceMetrics
GeneralIssues
SelectingGoldStandards
PartitioningthePatternsforTraining，Testing，andValidation
CrossValidation
FitnessandFitnessFunctions
ParametricandNonparametricStatistics
PercentCorrect
AverageSum-squaredError
AbsoluteError
NormalizedError
EvolutionaryAlgorithmEffectivenessMetrics
Mann-WhitneyUTest
ReceiverOperatingCharacteristicCurves
RecallandPrecision
OtherROC-relatedMeasures
ConfusionMatrices
Chi-squareTest
Summary
Exercises

chapterelevenAnalysisandExplanation
SensitivityAnalysis
RelationFactors
ZuradaSensitivityAnalysis
EvolutionaryComputationSensitivityAnalysis
HintonDiagrams
ComputationalIntelligenceToolsforExplanationFacilities
ExplanationFacilityRequirements
NeuralNetworkExplanation
FuzzyExpertSystemExplanation
EvolutionaryComputationToolsforExplanation
AnExampleNeuralNetworkExplanationFacility
Summary
Exercises
Bibliography
Index
AbouttheAuthors