Statistical Features in Learning

1998/09/09 by Ion-Olimpiu Stamatescu, Stamatescu, Ion-Olimpiu
Physics and Astronomy · #Adaptation and Self-Organizing Systems (nlin.AO) #Condensed Matter (cond-mat) #FOS: Physical sciences #adap-org #cond-mat #nlin.AO

paper · pdf · doi:10.48550/arxiv.cond-mat/9809135

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

arxiv created 1998/09/30 · arxiv updated 2009/11/30

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.

Related

• Learning with incomplete information - and the mathematical structure behind it
• Combining Hebbian and reinforcement learning in a minibrain model
• Bidirectional communication in neural networks moderated by a Hebb-like learning rule
• Dynamics of Learning with Restricted Training Sets II: Tests and Applications
• Statistical Mechanical Analysis of the Dynamics of Learning in Perceptrons