Statistical Features in Learning

Abstract

We study some features of learning models based on "delayed" and undifferentiated reinforcement and realized by simple algorithms which may be considered of a very elementary nature. We show that a modification of the Hebb-rule works well for this problem in a neural network realization and study numerically its convergence properties. An illustration for a more "concrete" situation is provided.

13 pages, 7 figures; LEARNING'98 Madrid; 2 notations, 1 typo corrected