English

Learning structured data from unspecific reinforcement

Condensed Matter 2009-10-31 v1

Abstract

We show that a straightforward extension of a simple learning model based on the Hebb rule, the previously introduced Association-Reinforcement-Hebb-Rule, can cope with "delayed", unspecific reinforcement also in the case of structured data and lead to perfect generalization.

Cite

@article{arxiv.cond-mat/0001405,
  title  = {Learning structured data from unspecific reinforcement},
  author = {M. Biehl and R. Kuehn and I. -O. Stamatescu},
  journal= {arXiv preprint arXiv:cond-mat/0001405},
  year   = {2009}
}

Comments

13 pages, 3 figures