NeuroEvolutionary meta-optimization

Author

Lang, Andrew ; Stanley, Kenneth O.

fYear

2013

fDate

4-9 Aug. 2013

Firstpage

1

Lastpage

8

Abstract

This paper introduces a meta-optimization algorithm called NeuroEvolutionary Meta-Optimization (NEMO) that evolves an algorithm targeted at optimizing only within a specific problem class. More specifically, a form of neural network is evolved that acts as the controller of a kind of optimization algorithm that can potentially exploit problem class-specific structure. NEMO is demonstrated on several benchmark problems that confirm its ability to succeed on problems within the class on which it is trained. The key implication is that it is indeed possible to evolve this kind of meta-optimizer with a neural network-like structure, opening up a promising research direction in automatically evolving such class-specific optimizers.

Keywords

evolutionary computation; neural nets; NEMO algorithm; benchmark problems; class-specific optimizers; class-specific structure; meta-optimizer; network-like structure; neural network; neuroevolutionary meta-optimization algorithm; Approximation algorithms; Metasearch; Network topology; Neural networks; Optimization; Search problems; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks (IJCNN), The 2013 International Joint Conference on

Conference_Location

Dallas, TX

ISSN

2161-4393

Print_ISBN

978-1-4673-6128-6

Type

conf

DOI

10.1109/IJCNN.2013.6707097

Filename

6707097