Muutke küpsiste eelistusi

EVOLVE- A Bridge between Probability, Set Oriented Numerics and Evolutionary Computation 2013 ed. [Kõva köide]

Edited by , Edited by , Edited by , Edited by , Edited by , Edited by , Edited by
  • Formaat: Hardback, 414 pages, kõrgus x laius: 235x155 mm, kaal: 816 g, XXII, 414 p., 1 Hardback
  • Sari: Studies in Computational Intelligence 447
  • Ilmumisaeg: 11-Sep-2012
  • Kirjastus: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • ISBN-10: 3642327257
  • ISBN-13: 9783642327254
Teised raamatud teemal:
  • Kõva köide
  • Hind: 141,35 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 166,29 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
EVOLVE- A Bridge between Probability, Set Oriented Numerics and Evolutionary Computation 2013 ed.Suurem pilt
  • Formaat: Hardback, 414 pages, kõrgus x laius: 235x155 mm, kaal: 816 g, XXII, 414 p., 1 Hardback
  • Sari: Studies in Computational Intelligence 447
  • Ilmumisaeg: 11-Sep-2012
  • Kirjastus: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • ISBN-10: 3642327257
  • ISBN-13: 9783642327254
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9783642327254.html
Märksõnad:

The aim of this book is to provide a strong theoretical support for understanding and analyzing the behavior of evolutionary algorithms, as well as for creating a bridge between probability, set-oriented numerics and evolutionary computation.

The volume encloses a collection of contributions that were presented at the EVOLVE 2011 international workshop, held in Luxembourg, May 25-27, 2011, coming from invited speakers and also from selected regular submissions. The aim of EVOLVE is to unify the perspectives offered by probability, set oriented numerics and evolutionary computation. EVOLVE focuses on challenging aspects that arise at the passage from theory to new paradigms and practice, elaborating on the foundations of evolutionary algorithms and theory-inspired methods merged with cutting-edge techniques that ensure performance guarantee factors. EVOLVE is also intended to foster a growing interest for robust and efficient methods with a sound theoretical background.

The chapters enclose challenging theoretical findings, concrete optimization problems as well as new perspectives. By gathering contributions from researchers with different backgrounds, the book is expected to set the basis for a unified view and vocabulary where theoretical advancements may echo in different domains.



This book provides strong theoretical support for analyzing the behavior of evolutionary algorithms and for bridging probability, set-oriented numerics and evolutionary computation. Offers theoretical findings, optimization problems and new perspectives.

Arvustused

From the book reviews:

The book collects 12 papers and presents those in chapter form. All papers are thoroughly refereed. The papers are well structured and consistent in style and presentation. this book has an impressive collection of research papers on useful and interesting transdisciplinary topics. I can safely conclude that researchers looking to learn more in this area of research could benefit from this book. (S. E. Ahmed, Technometrics, Vol. 56 (1), February, 2014)

Part I Foundations, Probability and Evolutionary Computation
1 On the Foundations and the Applications of Evolutionary Computing
3(88)
Pierre Del Moral
Alexandru-Adrian Tantar
Emilia Tantar
1.1 Introduction
3(7)
1.1.1 From Evolutionary Computing to Particle Algorithms
6(4)
1.1.2 Outline of the
Chapter
10(1)
1.2 Basic Notation and Motivation
10(3)
1.3 Genetic Particle Models
13(3)
1.4 Positive Matrices and Particle Recipes
16(14)
1.4.1 Positive Matrices and Measures
16(2)
1.4.2 Interacting Particle Models
18(4)
1.4.3 Genealogical and Ancestral Structures
22(2)
1.4.4 Complete Genealogical Tree Model
24(2)
1.4.5 Particle Derivation and Conditioning Principles
26(4)
1.5 Some Application Domains
30(61)
1.5.1 Particle Absorption Models
30(6)
1.5.2 Signal Processing and Bayesian Inference
36(7)
1.5.3 Interacting Kalman Filters
43(3)
1.5.4 Stochastic Optimization Algorithms
46(7)
1.5.5 Analysis of Convergence under Uncertain Behavior
53(13)
1.5.6 Rare Events Stochastic Models
66(14)
References
80(11)
2 Incorporating Regular Vines in Estimation of Distribution Algorithms
91(32)
Rogelio Salinas-Gutierrez
Arturo Hernandez-Aguirre
Enrique R. Villa-Diharce
2.1 Introduction
91(1)
2.2 Estimation of Distribution Algorithms
92(3)
2.3 Copula Functions
95(5)
2.3.1 The Gaussian Copula
96(4)
2.4 Regular Vines
100(11)
2.4.1 Copula Entropy and Mutual Information
102(9)
2.5 EDAs Based on Regular Vines
111(5)
2.5.1 Description of the C-Vine EDA
111(1)
2.5.2 Description of the D-Vine EDA
112(1)
2.5.3 Incorporating the Gaussian Copula
113(3)
2.6 Conclusions
116(7)
References
117(6)
3 The Gaussian Polytree EDA with Copula Functions and Mutations
123(34)
Ignacio Segovia Dominguez
Arturo Hernandez Aguirre
Enrique Villa Diharce
3.1 Introduction
123(3)
3.2 Related Work
126(1)
3.3 The Gaussian Poly-Tree
127(4)
3.3.1 Construction of the GPT
127(3)
3.3.2 Simulating Data from a Poly-Tree
130(1)
3.4 The Gaussian Poly-Tree with Gaussian Copula Function
131(5)
3.4.1 Gaussian Copula Functions
132(2)
3.4.2 Building the Gaussian Copula Poly-Tree and Data Simulation
134(2)
3.5 Gaussian Poly-Trees with Gaussian Copula Functions + Mutations
136(1)
3.6 Experiments
137(14)
3.6.1 Experiment I: Contrasting the Gaussian Poly-Tree with the Dependence Tree
137(2)
3.6.2 Experiment 2: Solving Unimodal Functions with the GPT-EDA
139(1)
3.6.3 Experiment 3: Solving Multimodal Functions with the GPT-EDA
139(1)
3.6.4 Experiment 4: Solving Unimodal Functions with the GCPT-EDA
140(1)
3.6.5 Experiment 5: Solving Multimodal Functions with the GCPT-EDA
141(1)
3.6.6 Experiment 6: Solving Unimodal Functions with the GCPT-EDA + Mutations
141(3)
3.6.7 Experiment 7: Solving Multimodal Functions with the GCPT-EDA + Mutations
144(7)
3.7 Conclusions
151(6)
References
152(1)
Appendix A Test Function Difintions
153(4)
Part II Set Oriented Numerics
4 On Quality Indicators for Black-Box Level Set Approximation
157(30)
Michael T.M. Emmerich
Andre H. Deutz
Johannes W. Kruisselbrink
4.1 Introduction
157(3)
4.2 Related Work
160(1)
4.3 Decision Theoretic Motivation of Quality Indicators
160(11)
4.3.1 Pareto Order for Representativeness
161(1)
4.3.2 Lorenz Order for Representativeness
162(2)
4.3.3 Unary Indicators for Representativeness
164(3)
4.3.4 A Preference Order for Feasibility
167(1)
4.3.5 Combining Representativeness and Feasibility
168(2)
4.3.6 Diversity versus Representativeness
170(1)
4.4 Selected Quality Indicators and Their Properties
171(9)
4.4.1 Simple Spread Indicators
171(1)
4.4.2 Diversity Indicators
172(2)
4.4.3 Indicators Based on Distances between Sets
174(6)
4.5 Numerical Results
180(4)
4.5.1 Experimental Study
181(3)
4.6 Summary and Outlook
184(3)
References
184(3)
5 Set Oriented Methods for the Numerical Treatment of Multiobjective Optimization Problems
187(36)
Oliver Schutze
Katrin Witting
Sina Ober-Blobaum
Michael Dellnitz
5.1 Introduction
187(2)
5.2 Multiobjective Optimization
189(1)
5.3 A Subdivision Algorithm for the Computation of Relative Global Attractors
190(4)
5.3.1 The Relative Global Attractor
190(2)
5.3.2 The Algorithm
192(1)
5.3.3 Realization of the Algorithm
193(1)
5.4 Basic Algorithms for Multiobjective Optimization
194(13)
5.4.1 Subdivision Techniques
195(3)
5.4.2 Recover Techniques in Parameter Space
198(4)
5.4.3 Image-Set Oriented Recover Techniques
202(5)
5.5 Multiobjective Optimal Control Problems
207(8)
5.5.1 Differentially Flat Systems
207(4)
5.5.2 Lagrangian Systems
211(4)
5.6 Concluding Remarks
215(8)
References
216(7)
Part III Landscape, Coevolution and Cooperation
6 A Complex-Networks View of Hard Combinatorial Search Spaces
223(24)
Marco Tomassini
Fabio Daolio
6.1 Hard Problems, Search Spaces, and Fitness Landscapes
223(6)
6.1.1 Fitness Landscapes
224(3)
6.1.2 Local Optima Networks
227(1)
6.1.3 Some Definitions for Weighted Complex Networks
228(1)
6.2 Local Optima Networks of NK Landscapes
229(8)
6.2.1 Basins of Attraction
234(3)
6.3 LONs for the QAP Fitness Landscapes
237(6)
6.3.1 General Network Features
238(3)
6.3.2 Optima Distribution and Clustering
241(2)
6.4 Conclusions and Prospects
243(4)
References
244(3)
7 Cooperative Coevolution for Agrifood Process Modeling
247(42)
Olivier Barriere
Evelyne Lutton
Pierre-Henri Wuillemin
Cedric Baudrit
Mariette Sicard
Nathalie Perrot
7.1 Introduction
248(2)
7.2 Modeling Agri-Food Industrial Processes
250(3)
7.2.1 The Camembert-Cheese Ripening Process
250(2)
7.2.2 Modeling Expertise on Cheese Ripening
252(1)
7.3 Phase Estimation Using GP
253(10)
7.3.1 Phase Estimation Using a Classical GP
254(3)
7.3.2 Phase Estimation Using a Parisian GP
257(6)
7.4 Bayesian Network Structure Learning Using CCEAs
263(19)
7.4.1 Recall of Some Probability Notions
263(1)
7.4.2 Bayesian Networks
264(4)
7.4.3 Evolution of an Independence Model
268(3)
7.4.4 Sharing
271(1)
7.4.5 Immortal Archive and Embossing Points
272(1)
7.4.6 Description of the Main Parameters
273(1)
7.4.7 Bayesian Network Structure Estimation
273(2)
7.4.8 Experiments and Results
275(6)
7.4.9 Analysis
281(1)
7.5 Conclusion
282(7)
References
283(6)
8 Hybridizing cGAs with PSO-like Mutation
289(16)
E. Alba
A. Villagra
8.1 Introduction
289(1)
8.2 Basic Concepts
290(3)
8.2.1 Particle Swarm Optimization
291(1)
8.2.2 Cellular Genetic Algorithm
292(1)
8.3 Active Components of PSO into cGA
293(2)
8.4 Experiments and Analysis of Results
295(5)
8.5 Conclusions and Further Work
300(5)
References
301(4)
Part IV Multi-objective Optimization, Heuristic Conversion Algorithms
9 On Gradient-Based Local Search to Hybridize Multi-objective Evolutionary Algorithms
305(28)
Adriana Lara
Oliver Schutze
Carlos A. Coello Coello
9.1 Introduction
305(3)
9.2 Descent Cones and Directions
308(4)
9.3 Practical Approaches
312(12)
9.3.1 Movements toward the Optimum
312(2)
9.3.2 Movements along the Pareto Set
314(6)
9.3.3 Directed Movements
320(4)
9.3.4 Step-Length Computation
324(1)
9.4 Toward the Hybridization
324(3)
9.4.1 Main Issues
324(2)
9.4.2 Early Hybrids
326(1)
9.5 Conclusions and New Trends
327(6)
References
329(4)
10 On the Integration of Theoretical Single-Objective Scheduling Results for Multi-objective Problems
333(32)
Christian Grimme
Markus Kemmerling
Joachim Lepping
10.1 Introduction
333(2)
10.2 Scheduling Problems and Theoretical Results
335(7)
10.2.1 Single-Objective
336(1)
10.2.2 Multi-objective
337(5)
10.2.3 The Gap between Single-Objective Theory and Multi-objective Approaches
342(1)
10.3 The Modular Predator-Prey Model
342(4)
10.4 Adopting the Predator-Prey Model to Scheduling Problems
346(6)
10.4.1 Variation Operator Design
346(2)
10.4.2 Evaluation
348(4)
10.5 Integrating a Self-adaptive Mechanism for Diversity Preservation
352(8)
10.5.1 Algorithmic Extension and Implementation
353(3)
10.5.2 Evaluation
356(4)
10.6 Conclusion
360(5)
References
361(4)
11 Analysing the Robustness of Multiobjectivisation Approaches Applied to Large Scale Optimisation Problems
365(28)
Carlos Segura
Eduardo Segredo
Coromoto Leon
11.1 Introduction
365(3)
11.2 Optimisation Schemes
368(2)
11.3 Multiobjectivisation
370(3)
11.4 Parameter Setting
373(3)
11.5 Increasing the Robustness of Multiobjectivisation
376(1)
11.6 Experimental Evaluation
377(10)
11.6.1 Performance of Multiobjectivisation
378(3)
11.6.2 On the Usage of Multiobjectivisation with Parameters
381(3)
11.6.3 Rising the Robusiness of Multiobjectivisation
384(2)
11.6.4 Analysing the Performance of Hyperheuristics with a Large Number of Variables
386(1)
11.7 Conclusions
387(6)
References
389(4)
12 A Comparative Study of Heuristic Conversion Algorithms, Genetic Programming and Return Predictability on the German Market
393
Esther Mohr
Gunter Schmidt
Sebastian Jansen
12.1 Introduction
393(2)
12.2 Related Work
395(5)
12.3 Problem Formulation
400(3)
12.3.1 Moving Average Crossover (MA)
401(1)
12.3.2 Trading Range Breakout (TRB)
402(1)
12.3.3 Genetic Programming (GP)
403(1)
12.4 Experimental Design
403(4)
12.4.1 Algorithms Considered
404(1)
12.4.2 Performance Measurement
405(2)
12.5 Results
407(4)
12.6 Conclusions
411
References
412