Evolving Neural Networks with Iterative Learning Scheme for Associative Memory
adap-org
2008-02-03 v1 Adaptation and Self-Organizing Systems
q-bio
Abstract
A locally iterative learning (LIL) rule is adapted to a model of the associative memory based on the evolving recurrent-type neural networks composed of growing neurons. There exist extremely different scale parameters of time, the individual learning time and the generation in evolution. This model allows us definite investigation on the interaction between learning and evolution. And the reinforcement of the robustness against the noise is also achieved in the evolutional scheme.
Cite
@article{arxiv.adap-org/9507008,
title = {Evolving Neural Networks with Iterative Learning Scheme for Associative Memory},
author = {Sh. Fujita and H. Nishimura},
journal= {arXiv preprint arXiv:adap-org/9507008},
year = {2008}
}
Comments
9 pages, compressed and uuencoded postscript file