On-line learning through simple perceptron learning with a margin

DOI10.1016/J.NEUNET.2003.08.005MaRDI QIDQ1877568zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Kazuyuki Hara, Masato Okada

Publication date 19 August 2004

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/0306150

zbMATH Keywords

On-line learningStatistical mechanicsMarginPerceptron learningGeneralization abilitySimple perceptron

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: We analyze a learning method that uses a margin $kappa$ {it a la} Gardner for simple perceptron learning. This method corresponds to the perceptron learning when $kappa=0$, and to the Hebbian learning when $kappaoinfty$. Nevertheless, we found that the generalization ability of the method was superior to that of the perceptron and the Hebbian methods at an early stage of learning. We analyzed the asymptotic property of the learning curve of this method through computer simulation and found that it was the same as for perceptron learning. We also investigated an adaptive margin control method.

Recommendations

• On-line learning of non-monotonic rules by simple perceptron
• scientific article; zbMATH DE number 1329967
• scientific article; zbMATH DE number 822102
• scientific article; zbMATH DE number 2226649
• On-line learning and generalization in coupled perceptrons

Cites work

• scientific article; zbMATH DE number 3231758 (Why is no real title available?)
• Optimal generalization in perceptions
• Statistical Physics of Spin Glasses and Information Processing
• The space of interactions in neural network models

Cited in

(4)

• On-line learning of non-monotonic rules by simple perceptron
• scientific article; zbMATH DE number 2226649 (Why is no real title available?)
• Non-monotonic convergence of online learning algorithms for perceptrons with noisy teacher
• The perceptron with dynamic margin

This page was built for publication: On-line learning through simple perceptron learning with a margin

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1877568)