Noisy regression and classification with continuous multilayer networks

DOI10.1088/0305-4470/32/50/101MaRDI QIDQ4495864zbMATH OpenOpenAlexWikidataFDO

Authors M. Ahr, Michael Biehl, R. Urbanczik

Publication date 13 August 2000

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/9907340

zbMATH Keywords

classificationmultilayer neural networksnoisy regressionreplica symmetry breakingunrealizable ruleszero-temperature Gibbs learning

Mathematics Subject Classification ID

Neural nets applied to problems in time-dependent statistical mechanics (82C32) Neural networks for/in biological studies, artificial life and related topics (92B20)

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. Further, the classification problem is shown to be formally equivalent to the noisy regression problem.

Recommendations

• Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise
• Learning from stochastic rules under finite temperature - optimal temperature and asymptotic learning curve
• Learning dynamics: a replica approach
• Phase transitions and learning in neural networks

Cited in

(1)

• Analytic continuation of noisy data using Adams Bashforth residual neural network

This page was built for publication: Noisy regression and classification with continuous multilayer networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4495864)