DMCA
The Use of Strategy Adaptation
Cached
Download Links
BibTeX
@MISC{Mache_theuse,
author = {D. H. Mache and J. Szabados and Christian Igel and Stefan Wiegand and Frauke Friedrichs},
title = {The Use of Strategy Adaptation},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We consider the synthesis of neural networks by evolutionary algorithms, which are randomized direct optimization methods inspired by neo-Darwinian evolution theory. Evolutionary algorithms in general as well as special variants for real-valued optimization and for search in the space of graphs are introduced. We put an emphasis on strategy adaptation, a feature of evolutionary methods that allows for the control of the search strategy during the optimization process. Three recent applications of evolutionary optimization of neural systems are presented: topology optimization of multi-layer neural networks for face detection, weight optimization of recurrent networks for solving reinforcement learning tasks, and hyperparameter tuning of support vector machines. 1
Keyphrases
strategy adaptation evolutionary algorithm recurrent network support vector machine evolutionary method recent application face detection weight optimization hyperparameter tuning evolutionary optimization search strategy reinforcement learning task multi-layer neural network direct optimization method real-valued optimization neural system neo-darwinian evolution theory special variant optimization process neural network topology optimization
