Proceedings of the Annual Conference of the Institute of Systems, Control and Information Engineers
The 52nd Annual Conference of the Institute of Systems, Control and Information Engineers
Session ID : 3F3-3
Conference information

On Evolutionary Design of Recurrent Neural Network Topologies Along with Weights
*Yuki MorikawaNaoki FuruyaTakanori IwasaNorihiko OnoYoshio Mogami
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract
The generation alternation model employed by one of the best neuroevolution methods, NEAT, has a drawback; it proceeds without intensively searching neighbors of parent individuals and hence it often fails in identifying solutions with minimal topologies. This paper presents an alternative for the model and discusses its effectiveness through the application to several non-Markovian tasks.
Content from these authors
© 2008 The Institute of Systems, Control and Information Engineers
Previous article Next article
feedback
Top