Learning from Mistakes
adap-org
2008-02-03 v1 凝聚态物理
适应与自组织系统
q-bio
摘要
A simple model of self-organised learning with no classical (Hebbian) reinforcement is presented. Synaptic connections involved in mistakes are depressed. The model operates at a highly adaptive, probably critical, state reached by extremal dynamics similar to that of recent evolution models. Thus, one might think of the mechanism as synaptic Darwinism.
引用
@article{arxiv.adap-org/9707006,
title = {Learning from Mistakes},
author = {Dante R. Chialvo and Per Bak},
journal= {arXiv preprint arXiv:adap-org/9707006},
year = {2008}
}
备注
12 pages, Latex2e