Learning structured data from unspecific reinforcement
arXiv:cond-mat/0001405 · doi:10.1088/0305-4470/33/39/302
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.
13 pages, 3 figures