Machine Learning for Evolution Strategies

Kramer, Oliver

ISBN 10: 3319815008 / ISBN 13: 9783319815008

Verlag: Springer, 2018

2018. Paperback. . . . . . Bestandsnummer des Verkäufers V9783319815008

Inhaltsangabe:

This book introduces numerous algorithmic hybridizations between both worlds that show how machine learning can improve and support evolution strategies. The set of methods comprises covariance matrix estimation, meta-modeling of fitness and constraint functions, dimensionality reduction for search and visualization of high-dimensional optimization processes, and clustering-based niching. After giving an introduction to evolution strategies and machine learning, the book builds the bridge between both worlds with an algorithmic and experimental perspective. Experiments mostly employ a (1+1)-ES and are implemented in Python using the machine learning library scikit-learn. The examples are conducted on typical benchmark problems illustrating algorithmic concepts and their experimental behavior. The book closes with a discussion of related lines of research.

Von der hinteren Coverseite:

This bookintroduces numerous algorithmic hybridizations between both worlds that showhow machine learning can improve and support evolution strategies. The set ofmethods comprises covariance matrix estimation, meta-modeling of fitness andconstraint functions, dimensionality reduction for search and visualization ofhigh-dimensional optimization processes, and clustering-based niching. Aftergiving an introduction to evolution strategies and machine learning, the bookbuilds the bridge between both worlds with an algorithmic and experimentalperspective. Experiments mostly employ a (1+1)-ES and are implemented in Pythonusing the machine learning library scikit-learn. The examples are conducted ontypical benchmark problems illustrating algorithmic concepts and theirexperimental behavior. The book closes with a discussion of related lines ofresearch.

Bibliografische Details

Titel: Machine Learning for Evolution Strategies
Verlag: Springer
Erscheinungsdatum: 2018
Einband: Softcover
Zustand: New