Dynamics of learning with restricted training sets

Abstract

The dynamics of supervised learning in layered neural networks were studied in the regime where the size of the training set is proportional to the number of inputs. The evolution of macroscopic observables, including the two relevant performance measures can be predicted by using the dynamical replica theory. Three approximation schemes aimed at eliminating the need to solve a functional saddle-point equation at each time step have been derived.

Publication DOI: https://doi.org/10.1103/PhysRevE.62.5444
Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: Copyright of American Physical Society
Uncontrolled Keywords: layered neural networks,learning dynamics,dynamically replica theory,Mathematical Physics,Physics and Astronomy(all),Condensed Matter Physics,Statistical and Nonlinear Physics
Publication ISSN: 1550-2376
Last Modified: 05 Mar 2024 08:08
Date Deposited: 10 Aug 2009 12:31
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
http://link.aps ... hysRevE.62.5444 (Publisher URL)
PURE Output Type: Article
Published Date: 2000-10
Authors: Coolen, Anthony C.C.
Saad, David (ORCID Profile 0000-0001-9821-2623)

Download

[img]

Version: Accepted Version


Export / Share Citation


Statistics

Additional statistics for this record