Mean-field theory of learning: from dynamics to statics

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

Using the cavity method and diagrammatic methods, we model the dynamics of batch learning of restricted sets of examples. Simulations of the Green's function and the cavity activation distributions support the theory well. The learning dynamics approaches a steady state in agreement with the static version of the cavity method. The picture of the rough energy landscape is reviewed.
13 pages, 5 figures, to appear in "Advanced Mean Field Methods - Theory and Practice", edited by M. Opper and D. Saad, MIT Press

Keywords

Disordered Systems and Neural Networks

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/16478

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/cond-mat/0006251
 http://arxiv.org/abs/cond-mat/0006251

Collections

arXiv