APS » PROLA » Rev. Mod. Phys. » Volume 65 » Issue 2

Rev. Mod. Phys. 65, 499 - 556 (1993)

The statistical mechanics of learning a rule

Download: Page Images , PDF (11597 kB), or Buy this Article (Use Article Pack) Export: BibTeX or EndNote (RIS)

Timothy L. H. Watkin * and Albrecht Rau †
Department of Physics, University of Oxford, Oxford OX1 3NP, United Kingdom

Michael Biehl
Physikalisches Institut, Julius-Maximilians-Universität, Am Hubland, D-8700 Würzburg, Germany

A summary is presented of the statistical mechanical theory of learning a rule with a neural network, a rapidly advancing area which is closely related to other inverse problems frequently encountered by physicists. By emphasizing the relationship between neural networks and strongly interacting physical systems, such as spin glasses, the authors show how learning theory has provided a workshop in which to develop new, exact analytical techniques.


©1993 The American Physical Society

URL: http://link.aps.org/abstract/RMP/v65/p499
DOI: 10.1103/RevModPhys.65.499

* Present address: St. Johns College, Cambridge CB2 ITP, United Kingdom.
† Present address: Patentanwälte Schwabe, Sandmair, Marx, Stuntzstr. 16, D-8000 München 80, Germany.

[ Abstract  |  Previous article  |  Next article  |  Issue 2 ]