Learning in ultrametric committee machines

Abstract

The problem of learning by examples in ultrametric committee machines (UCMs) is studied within the framework of statistical mechanics. Using the replica formalism we calculate the average generalization error in UCMs with L hidden layers and for a large enough number of units. In most of the regimes studied we find that the generalization error, as a function of the number of examples presented, develops a discontinuous drop at a critical value of the load parameter. We also find that when L>1 a number of teacher networks with the same number of hidden layers and different overlaps induce learning processes with the same critical points.

Publication DOI: https://doi.org/10.1007/s10955-012-0636-1
Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: The original publication is available at www.springerlink.com
Uncontrolled Keywords: multilayered networks,learning by examples,Statistical and Nonlinear Physics,Mathematical Physics
Publication ISSN: 1572-9613
Last Modified: 24 Jan 2024 08:05
Date Deposited: 20 Dec 2012 09:57
Full Text Link: http://www.spri ... 35847k88l8h18n/
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2012-11
Published Online Date: 2012-11-21
Authors: Neirotti, Juan (ORCID Profile 0000-0002-2409-8917)

Download

[img]

Version: Accepted Version


Export / Share Citation


Statistics

Additional statistics for this record