Volume 6 : Number 1 : Paper 5 |
|
December 2003 Special Issue of Best Papers presented at CLEI'2002. Montevideo, Uruguay. Guest Editor: Alfredo Viola.
|
Title:
Evolving Neural Arrays A new mechanism for learning complex action sequences
Authors and Affiliations:
Leonardo Corbolan,
Laura Lanzarini, Universidad Nacional de La Plata, Facultad de Inform
Abstract:
Incremental evolution has proved to be an extremely useful mechanism in complex actions sequence
learning. Its performance is based on the decomposition of the original problem into increasingly
complex stages whose learning is carried out sequentially, starting from the simplest stage and thus
increasing its generality and difficulty.
The present work proposes neural array applications as a novel mechanism for complex actions
sequence learning. Each array is composed by several neural nets obtained by means of an evolving
process allowing them to acquire various degrees of specialization. Neural nets constituting the same
array are organized so that, in each assessment, there is only one in charge of its response.
The proposed strategy is applied to problems presented by obstacle evasion and target reaching as a
means to show the capability of this proposal to solve complex problems. The measurements carried
out show the superiority of evolving neural arrays over traditional neuroevolving methods that handle
neural network populations
|
Received May 2004, Revised
, Editor: Alfredo Viola
Full paper, 14 pages
[
PDF, 587 Kb ]
|
|
|
|
