Parallel strategy for optimal learning in perceptrons


We developed a parallel strategy for learning optimally specific realizable rules by perceptrons, in an online learning scenario. Our result is a generalization of the Caticha–Kinouchi (CK) algorithm developed for learning a perceptron with a synaptic vector drawn from a uniform distribution over the N-dimensional sphere, so called the typical case. Our method outperforms the CK algorithm in almost all possible situations, failing only in a denumerable set of cases. The algorithm is optimal in the sense that it saturates Bayesian bounds when it succeeds.

Publication DOI:
Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: © 2010 IOP Publishing Ltd.
Uncontrolled Keywords: learning,realizable rules,perceptrons,Caticha–Kinouchi algorithm,synaptic vector,N-dimensional sphere,Bayesian bounds,Mathematical Physics,Modelling and Simulation,Statistics and Probability,Physics and Astronomy(all),Statistical and Nonlinear Physics
Publication ISSN: 1751-8121
Last Modified: 17 Jun 2024 07:10
Date Deposited: 14 Dec 2011 12:24
Full Text Link: http://iopscien ... 1/43/12/125101/
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2010-03-26
Authors: Neirotti, Juan P. (ORCID Profile 0000-0002-2409-8917)


Export / Share Citation


Additional statistics for this record