University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Evolving neural fields for problems with large input and output spaces

Inden, B, Jin, Y, Haschke, R and Ritter, H (2012) Evolving neural fields for problems with large input and output spaces Neural Networks, 28. 24 - 39. ISSN 0893-6080

[img]
Preview
PDF
NEATfieldsRep6.pdf - Accepted Version
Available under License : See the attached licence file.

Download (889kB)
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf

Download (33kB)

Abstract

We have developed an extension of the NEAT neuroevolution method, called NEATfields, to solve problems with largeinput and outputspaces. The NEATfields method is a multilevel neuroevolution method using externally specified design patterns. Its networks have three levels of architecture. The highest level is a NEAT-like network of neuralfields. The intermediate level is a field of identical subnetworks, called field elements, with a two-dimensional topology. The lowest level is a NEAT-like subnetwork of neurons. The topology and connection weights of these networks are evolved with methods derived from the NEAT method. Evolution is provided with further design patterns to enable information flow between field elements, to dehomogenize neuralfields, and to enable detection of local features. We show that the NEATfields method can solve a number of high dimensional pattern recognition and control problems, provide conceptual and empirical comparison with the state of the art HyperNEAT method, and evaluate the benefits of different design patterns.

Item Type: Article
Additional Information: NOTICE: this is the author’s version of a work that was accepted for publication in Neural Networks. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Neural Networks, 28, April 2012, DOI 10.1016/j.neunet.2012.01.001.
Divisions: Faculty of Engineering and Physical Sciences > Computing Science
Depositing User: Symplectic Elements
Date Deposited: 03 May 2012 08:13
Last Modified: 23 Sep 2013 19:25
URI: http://epubs.surrey.ac.uk/id/eprint/532109

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800