Generalization performance of complex adaptive tasks

E. Eisenstein, I. Kanter

Research output: Contribution to journalArticlepeer-review

Abstract

Optimal strategies for predicting correctly the output of a few new random inputs, when various feedforward networks are trained by noise-free random training examples, are examined analytically and numerically. The existence of a universal strategy for various generalization tasks is discussed, and indicates that the Bayes algorithm is not always the optimal strategy.

Original languageEnglish
Pages (from-to)3667-3670
Number of pages4
JournalPhysical Review Letters
Volume70
Issue number23
DOIs
StatePublished - 7 Jun 1993

Fingerprint

Dive into the research topics of 'Generalization performance of complex adaptive tasks'. Together they form a unique fingerprint.

Cite this