Noisy regression and classification with continuous multilayer networks

M. Ahr, M. Biehl, R. Urbanczik

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)

Abstract

We investigate zero-temperature Gibbs learning for two classes of unrealizable rules which play an important role in practical applications of multilayer neural networks with differentiable activation functions: classification problems and noisy regression problems. Considering one step of replica symmetry breaking, we surprisingly find that for sufficiently large training sets the stable state is replica symmetric even though the target rule is unrealizable. Furthermore, the classification problem is shown to be formally equivalent to the noisy regression problem.
Original languageEnglish
Pages (from-to)L531-L536
Number of pages6
JournalJournal of Physics A, Mathematical and General
Volume32
Issue number50
DOIs
Publication statusPublished - 1-Dec-1999
Externally publishedYes

Cite this