On optimal neural network learning

T.L.H. Watkin

Physica A: Statistical Mechanics and its Applications, 1993, vol. 200, issue 1, 628-635

Abstract: We introduce optimal learning with a neural network, which we define as building a network with a minimal expectation generalisation error. This procedure may be analysed exactly in idealized problems by exploiting the relationship between sampling a space of hypotheses and the replica method of statistical physics. We find that the optimally trained spherical perceptron may learn a linearly separable rule as well as any possible computer, and present simulation results supporting our conclusions. Optimal learning of a well-known unlearnable problem, the “mismatched weight” problem, gives better asymptotic learning than conventional techniques, and may be simulated more easily. Unlike many other perceptron learning schemes, optimal learning extends to more general networks learning more complex rules.

Date: 1993
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/037843719390569P
Full text for ScienceDirect subscribers only. Journal offers the option of making the article available online on Science direct for a fee of $3,000

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:phsmap:v:200:y:1993:i:1:p:628-635

DOI: 10.1016/0378-4371(93)90569-P

Access Statistics for this article

Physica A: Statistical Mechanics and its Applications is currently edited by K. A. Dawson, J. O. Indekeu, H.E. Stanley and C. Tsallis

More articles in Physica A: Statistical Mechanics and its Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().