Muutke küpsiste eelistusi

Computational Intelligence: A Methodological Introduction 2nd Revised edition [Kõva köide]

3.25/5 (5 hinnangut Goodreads-ist)
Contributions by , Contributions by , , , , ,
  • Formaat: Hardback, 564 pages, kõrgus x laius: 235x155 mm, kaal: 1027 g, 255 black & white illustrations, biography
  • Sari: Texts in Computer Science
  • Ilmumisaeg: 17-Sep-2016
  • Kirjastus: Springer London Ltd
  • ISBN-10: 1447172949
  • ISBN-13: 9781447172949
Teised raamatud teemal:
  • Kõva köide
  • Hind: 81,12 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 95,44 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Computational Intelligence: A Methodological Introduction 2nd Revised editionSuurem pilt
  • Formaat: Hardback, 564 pages, kõrgus x laius: 235x155 mm, kaal: 1027 g, 255 black & white illustrations, biography
  • Sari: Texts in Computer Science
  • Ilmumisaeg: 17-Sep-2016
  • Kirjastus: Springer London Ltd
  • ISBN-10: 1447172949
  • ISBN-13: 9781447172949
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781447172949.html
Märksõnad:
This textbook provides a clear and logical introduction to the field, covering the fundamental concepts, algorithms and practical implementations behind efforts to develop systems that exhibit intelligent behavior in complex environments. This enhanced second edition has been fully revised and expanded with new content on swarm intelligence, deep learning, fuzzy data analysis, and discrete decision graphs. Features: provides supplementary material at an associated website; contains numerous classroom-tested examples and definitions throughout the text; presents useful insights into all that is necessary for the successful application of computational intelligence methods; explains the theoretical background underpinning proposed solutions to common problems; discusses in great detail the classical areas of artificial neural networks, fuzzy systems and evolutionary algorithms; reviews the latest developments in the field, covering such topics as ant colony optimization and probabilistic graphical models.
1 Introduction to Computational Intelligence
1(8)
1.1 Intelligent Systems
1(1)
1.2 Computational Intelligence
2(2)
1.3 About the Second Edition of This Book
4(5)
References
5(4)
Part I Neural Networks
2 Introduction to Neural Networks
9(6)
2.1 Motivation
9(2)
2.2 Biological Background
11(4)
References
13(2)
3 Threshold Logic Units
15(22)
3.1 Definition and Examples
15(2)
3.2 Geometric Interpretation
17(2)
3.3 Limitations
19(1)
3.4 Networks of Threshold Logic Units
20(3)
3.5 Training the Parameters
23(10)
3.6 Variants
33(1)
3.7 Training Networks
33(4)
References
34(3)
4 General Neural Networks
37(10)
4.1 Structure of Neural Networks
37(3)
4.2 Operation of Neural Networks
40(4)
4.3 Training Neural Networks
44(3)
5 Multilayer Perceptrons
47(46)
5.1 Definition and Examples
47(6)
5.2 Function Approximation
53(6)
5.3 Logistic Regression
59(2)
5.4 Gradient Descent
61(4)
5.5 Error Backpropagation
65(3)
5.6 Gradient Descent Examples
68(4)
5.7 Variants of Gradient Descent
72(5)
5.7.1 Manhattan Training
72(1)
5.7.2 Lifting the Derivative of the Activation Function
73(1)
5.7.3 Momentum Term
73(1)
5.7.4 Self-Adaptive Error Backpropagation
74(1)
5.7.5 Resilient Error Backpropagation
75(1)
5.7.6 Quick-Propagation
75(2)
5.7.7 Weight Decay
77(1)
5.8 Examples for Some Variants
77(2)
5.9 Number of Hidden Neurons
79(3)
5.10 Deep Learning
82(7)
5.11 Sensitivity Analysis
89(4)
References
91(2)
6 Radial Basis Function Networks
93(20)
6.1 Definition and Examples
93(5)
6.2 Function Approximation
98(3)
6.3 Initializing the Parameters
101(6)
6.4 Training the Parameters
107(4)
6.5 Generalized Form
111(2)
References
112(1)
7 Self-organizing Maps
113(18)
7.1 Definition and Examples
113(3)
7.2 Learning Vector Quantization
116(7)
7.3 Neighborhood of the Output Neurons
123(1)
7.3 Neighborhood of the Output Neurons
123(8)
References
128(3)
8 Hopfield Networks
131(28)
8.1 Definition and Examples
131(4)
8.2 Convergence of the Computations
135(4)
8.3 Associative Memory
139(5)
8.4 Solving Optimization Problems
144(6)
8.5 Simulated Annealing
150(1)
8.6 Boltzmann Machines
151(8)
References
156(3)
9 Recurrent Networks
159(14)
9.1 Simple Examples
159(5)
9.2 Representing Differential Equations
164(2)
9.3 Vectorial Neural Networks
166(3)
9.4 Error Backpropagation in Time
169(4)
References
171(2)
10 Mathematical Remarks for Neural Networks
173(10)
10.1 Equations for Straight Lines
173(2)
10.2 Regression
175(4)
10.3 Activation Transformation
179(4)
Reference
180(3)
Part II Evolutionary Algorithms
11 Introduction to Evolutionary Algorithms
183(30)
11.1 Metaheuristics
183(1)
11.2 Biological Evolution
184(5)
11.3 Simulated Evolution
189(8)
11.3.1 Optimization Problems
189(3)
11.3.2 Basic Notions and Concepts
192(3)
11.3.3 Building Blocks of an Evolutionary Algorithm
195(2)
11.4 The n-Queens Problem
197(5)
11.5 Related Optimization Techniques
202(6)
11.5.1 Gradient Ascent or Descent
203(2)
11.5.2 Hill Climbing
205(1)
11.5.3 Simulated Annealing
206(1)
11.5.4 Threshold Accepting
206(1)
11.5.5 Great Deluge Algorithm
207(1)
11.5.6 Record-to-Record Travel
207(1)
11.6 The Traveling Salesman Problem
208(5)
References
211(2)
12 Elements of Evolutionary Algorithms
213(32)
12.1 Encoding of Solution Candidates
213(7)
12.1.1 Hamming Cliffs
214(2)
12.1.2 Epistasis
216(2)
12.1.3 Closedness of the Search Space
218(2)
12.2 Fitness and Selection
220(12)
12.2.1 Fitness Proportionate Selection
221(1)
12.2.2 The Dominance Problem
222(1)
12.2.3 Vanishing Selective Pressure
223(2)
12.2.4 Adapting the Fitness Function
225(2)
12.2.5 The Variance Problem
227(1)
12.2.6 Rank-Based Selection
228(1)
12.2.7 Tournament Selection
229(1)
12.2.8 Elitism
230(1)
12.2.9 Niche Techniques
231(1)
12.2.10 Characterization of Selection Methods
231(1)
12.3 Genetic Operators
232(13)
12.3.1 Mutation Operators
233(3)
12.3.2 Crossover Operators
236(4)
12.3.3 Multi-parent Operators
240(1)
12.3.4 Characteristics of Recombination Operators
241(1)
12.3.5 Interpolating and Extrapolating Recombination
242(1)
References
243(2)
13 Fundamental Evolutionary Algorithms
245(54)
13.1 Genetic Algorithms
245(12)
13.1.1 The Schema Theorem
247(7)
13.1.2 The Two-Armed Bandit Argument
254(2)
13.1.3 The Principle of Minimal Alphabets
256(1)
13.2 Evolution Strategies
257(11)
13.2.1 Selection
258(1)
13.2.2 Global Variance Adaptation
259(2)
13.2.3 Local Variance Adaptation
261(1)
13.2.4 Co variances
262(5)
13.2.5 Recombination Operators
267(1)
13.3 Genetic Programming
268(12)
13.3.1 Initialization
271(2)
13.3.2 Genetic Operators
273(2)
13.3.3 Application Examples
275(4)
13.3.4 The Problem of Introns
279(1)
13.3.5 Extensions
280(1)
13.4 Multi-criteria Optimization
280(7)
13.4.1 Weighted Combination of Criteria
281(1)
13.4.2 Pareto-Optimal Solutions
281(2)
13.4.3 Finding Pareto-Frontiers with Evolutionary Algorithms
283(4)
13.5 Special Applications and Techniques
287(12)
13.5.1 Behavioral Simulation
288(6)
13.5.2 Parallelization
294(2)
References
296(3)
14 Computational Swarm Intelligence
299(30)
14.1 Introduction
299(1)
14.2 Basic Principles of Computational Swarm Intelligence
300(5)
14.2.1 Swarms in Known Environments
303(1)
14.2.2 Swarms in Unknown Environments
304(1)
14.3 Particle Swarm Optimization
305(4)
14.3.1 Influence of the Parameters
307(1)
14.3.2 Turbulence Factor
308(1)
14.3.3 Boundary Handling
308(1)
14.4 Multi-objective Particle Swarm Optimization
309(7)
14.4.1 Leader Selection Mechanism
310(2)
14.4.2 Archiving
312(4)
14.5 Many-Objective Particle Swarm Optimization
316(1)
14.5.1 Ranking Non-dominated Solutions
316(1)
14.5.2 Distance Based Ranking
317(1)
14.6 Ant Colony Optimization
317(12)
References
324(5)
Part III Fuzzy Systems
15 Introduction to Fuzzy Sets and Fuzzy Logic
329(32)
15.1 Natural Languages and Formal Models
329(1)
15.2 Fuzzy Sets
330(2)
15.3 Interpretation of Fuzzy Sets
332(3)
15.3.1 Gradual Membership is Different from Probability
332(1)
15.3.2 Fuzzy Sets for Modeling Similarity
333(1)
15.3.3 Fuzzy Sets for Modeling Preference
334(1)
15.3.4 Fuzzy Sets for Modeling Possibility
334(1)
15.3.5 Consistent Interpretations of Fuzzy Sets in Applications
334(1)
15.4 Representation of Fuzzy Sets
335(5)
15.4.1 Definition Based on Functions
336(2)
15.4.2 Level Sets
338(2)
15.5 Fuzzy Logic
340(10)
15.5.1 Propositions and Truth Values
340(3)
15.5.2 t-Norms and t-Conorms
343(5)
15.5.3 Aggregation Functions
348(1)
15.5.4 Basic Assumptions and Problems
349(1)
15.6 Operations on Fuzzy Sets
350(5)
15.6.1 Intersection
350(2)
15.6.2 Union
352(1)
15.6.3 Complement
353(1)
15.6.4 Linguistic Modifiers
354(1)
15.7 Extensions of Fuzzy Set Theory
355(6)
References
358(3)
16 The Extension Principle
361(8)
16.1 Mappings of Fuzzy Sets
361(2)
16.2 Mapping of Level Sets
363(1)
16.3 Cartesian Product and Cylindrical Extension
364(1)
16.4 Extension Principle for Multivariate Mappings
365(4)
References
367(2)
17 Fuzzy Relations
369(14)
17.1 Crisp Relations
369(2)
17.2 Application of Relations and Deduction
371(2)
17.3 Chains of Deductions
373(2)
17.4 Simple Fuzzy Relations
375(4)
17.5 Composition of Fuzzy Relations
379(2)
17.6 Fuzzy Relational Equations
381(2)
References
382(1)
18 Similarity Relations
383(12)
18.1 Similarity
383(1)
18.2 Fuzzy Sets and Extensional Hulls
384(2)
18.3 Scaling Concepts
386(3)
18.4 Fuzzy Sets and Similarity Relations
389(6)
References
393(2)
19 Fuzzy Control
395(36)
19.1 Mamdani Controllers
395(10)
19.1.1 Remarks on Fuzzy Controller Design
399(3)
19.1.2 Defuzzification Methods
402(3)
19.2 Takagi--Sugeno--Kang Controllers
405(2)
19.3 Mamdani Controller and Similarity Relations
407(3)
19.3.1 Interpretation of a Controller
407(2)
19.3.2 Construction of a Controller
409(1)
19.4 Logic-Based Controllers
410(2)
19.5 Control Based on Fuzzy Relational Equations
412(1)
19.6 Hybrid Systems to Tune Fuzzy Controllers
413(18)
19.6.1 Neuro-Fuzzy Control
414(9)
19.6.2 Evolutionary Fuzzy Control
423(5)
References
428(3)
20 Fuzzy Data Analysis
431(28)
20.1 Fuzzy Methods in Data Analysis
431(1)
20.2 Fuzzy Clustering
432(13)
20.2.1 Clustering
433(1)
20.2.2 Presuppositions and Notation
433(1)
20.2.3 Classical c-Means Clustering
434(2)
20.2.4 Fuzzification by Membership Transformation
436(3)
20.2.5 Fuzzification by Membership Regularization
439(5)
20.2.6 Comparison
444(1)
20.3 Analysis of Imprecise Data Using Random Sets
445(2)
20.4 Possibility Theory and Generalized Measures
447(3)
20.5 Fuzzy Random Variables
450(9)
References
453(6)
Part IV Bayes and Markov Networks
21 Introduction to Bayes Networks
459(6)
22 Elements of Probability and Graph Theory
465(28)
22.1 Probability Theory
465(9)
22.1.1 Random Variables and Random Vectors
468(4)
22.1.2 Independences
472(2)
22.2 Graph Theory
474(19)
22.2.1 Background
474(8)
22.2.2 Join Graphs
482(3)
22.2.3 Separations
485(6)
References
491(2)
23 Decompositions
493(14)
References
504(3)
24 Evidence Propagation
507(14)
24.1 Initialization
511(7)
24.1.1 Message Passing
511(1)
24.1.2 Update
512(1)
24.1.3 Marginalization
512(5)
24.1.4 Derivation
517(1)
24.2 Other Propagation Algorithms
518(3)
References
519(2)
25 Learning Graphical Models
521(10)
References
530(1)
26 Belief Revision
531(10)
26.1 Introduction
531(2)
26.2 Revision Procedure
533(2)
26.3 A Real-World Application
535(6)
26.3.1 Knowledge Representation
536(2)
References
538(3)
27 Decision Graphs
541(12)
27.1 Motivation
541(2)
27.2 Definition
543(3)
27.3 Policies and Strategies
546(1)
27.4 Finding Optimal Strategies
546(2)
27.5 Example Scenario
548(5)
References
551(2)
Index 553
Rudolf Kruse and Sanaz Mostaghim are professors at the Department of Computer Science of the Otto von Guericke University of Magdeburg, Germany. Christian Borgelt is a principal researcher, and Christian Braune is a research assistant at the same institution. Matthias Steinbrecher is with SAP SE, Potsdam, Germany.