Notice bibliographique
- Notice
Type(s) de contenu et mode(s) de consultation : Texte noté : électronique
Titre(s) : Scalable optimization via probabilistic modeling [Texte électronique] : from algorithms to applications / Martin Pelikan, Kumara Sastry, Erick Cantu-Paz (eds.)
Publication : Berlin ; New York : Springer, cop. 2006
Description matérielle : 1 online resource (xx, 349 pages)
Collection : Studies in computational intelligence ; v. 33
Note(s) : Includes bibliographical references
This book focuses like a laser beam on one of the hottest topics in evolutionary computation
over the last decade or so: estimation of distribution algorithms (EDAs). EDAs are
an important current technique that is leading to breakthroughs in genetic and evolutionary
computation and in optimization more generally. I'm putting Scalable Optimization
via Probabilistic Modeling in a prominent place in my library, and I urge you to do
so as well. This volume summarizes the state of the art at the same time it points
to where that art is going. Buy it, read it, and take its lessons to heart. David
E Goldberg, University of Illinois at Urbana-Champaign This book is an excellent compilation
of carefully selected topics in estimation of distribution algorithms--search algorithms
that combine ideas from evolutionary algorithms and machine learning. The book covers
a broad spectrum of important subjects ranging from design of robust and scalable
optimization algorithms to efficiency enhancements and applications of these algorithms.
The book should be of interest to theoreticians and practitioners alike, and is a
must-have resource for those interested in stochastic optimization in general, and
genetic and evolutionary algorithms in particular. John R. Koza, Stanford University
This edited book portrays population-based optimization algorithms and applications,
covering the entire gamut of optimization problems having single and multiple objectives,
discrete and continuous variables, serial and parallel computations, and simple and
complex function models. Anyone interested in population-based optimization methods,
either knowingly or unknowingly, use some form of an estimation of distribution algorithm
(EDA). This book is an eye-opener and a must-read text, covering easy-to-read yet
erudite articles on established and emerging EDA methodologies from real experts in
the field. Kalyanmoy Deb, Indian Institute of Technology Kanpur This book is an excellent
comprehensive resource on estimation of distribution algorithms. It can serve as the
primary EDA resource for practitioner or researcher. The book includes chapters from
all major contributors to EDA state-of-the-art and covers the spectrum from EDA design
to applications. These algorithms strategically combine the advantages of genetic
and evolutionary computation with the advantages of statistical, model building machine
learning techniques. EDAs are useful to solve classes of difficult real-world problems
in a robust and scalable manner. Una-May O'Reilly, Massachusetts Institute of Technology
Machine-learning methods continue to stir the public's imagination due to its futuristic
implications. But, probability-based optimization methods can have great impact now
on many scientific multiscale and engineering design problems, especially true with
use of efficient and competent genetic algorithms (GA) which are the basis of the
present volume. Even though efficient and competent GAs outperform standard techniques
and prevent negative issues, such as solution stagnation, inherent in the older but
more well-known GAs, they remain less known or embraced in the scientific and engineering
communities. To that end, the editors have brought together a selection of experts
that (1) introduce the current methodology and lexicography of the field with illustrative
discussions and highly useful references, (2) exemplify these new techniques that
dramatic improve performance in provable hard problems, and (3) provide real-world
applications of these techniques, such as antenna design. As one who has strayed into
the use of genetic algorithms and genetic programming for multiscale modeling in materials
science, I can say it would have been personally more useful if this would have come
out five years ago, but, for my students, it will be a boon. Duane D. Johnson, University
of Illinois at Urbana-Champaign
Autre(s) auteur(s) : Pelikan, Martin. Fonction indéterminée
Sastry, Kumara. Fonction indéterminée
Cantú-Paz, Erick. Fonction indéterminée
Sujet(s) : Optimisation combinatoire
Calcul évolutionnaire
Algorithmes génétiques
Apprentissage automatique
Identifiants, prix et caractéristiques : ISBN 9783540349549
Identifiant de la notice : ark:/12148/cb44686837q
Notice n° :
FRBNF44686837
(notice reprise d'un réservoir extérieur)
Table des matières : Introduction / Martin Pelikan, Kumara Sastry, Erick Cantú-Paz ; Factorized distribution algorithm and the minimum relative entropy principle / Heinz Mühlenbein, Robin Höns ; Linkage learning via probabilistic modeling in the extended compact genetic algorithm (ECGA) / Georges R. Harik, Fernando G. Lobo, Kumara Sastry ; Hierarchical Bayesian optimization algorithm / Martin Peilkan, David E. Goldberg ; Numerical optimization of real-valued estimation-of-distribution algorithms / Peter A.N. Bosman, Dirk Thierens ; Survey of probabilistic model building genetic programming / Yin Shan [and others] ; Efficiency enhancement of estimation of distribution algorithms / Kumara Sastry, Martin Pelikan, David E. Goldberg ; Design of parallel estimation of distribution algorithms / Jiri Ocenasek [and others] ; Incorporating a priori knowledge in probabilistic-model based optimization / Shumeet Baluja ; Multiobjective estimation of distribution algorithms / Martin Pelikan, Kumara Sast