Accession Number:

ADA456062

Title:

ELeaRNT: Evolutionary Learning of Rich Neural Network Topologies

Descriptive Note:

Technical rept.

Corporate Author:

CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE

Personal Author(s):

Report Date:

2006-01-01

Pagination or Media Count:

15.0

Abstract:

In this paper we present ELeaRNT an evolutionary strategy which evolves rich neural network topologies in order to find an optimal domain specific non linear function approximator with a good generalization performance. The neural networks evolved by the algorithm have a feed forward topology with shortcut connections and arbitrary activation functions at each layer. This kind of topologies has not been thoroughly investigated in literature, but is particularly well suited for non linear regression tasks. The experimental results prove that, in such tasks, our algorithm can build, in a completely automated way, neural network topologies able to outperform classic neural network models designed by hand. Also when applied to classification problems, the performance of the obtained neural networks is fully comparable to that of classic neural networks and in some cases noticeably better.

Subject Categories:

  • Computer Systems
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE