On-line learning and generalization in coupled perceptrons

DOI10.1088/0305-4470/35/9/302zbMATH Open1002.82024arXivcond-mat/0111493OpenAlexW3106413330WikidataQ62596469 ScholiaQ62596469MaRDI QIDQ4545296FDOQ4545296

D. Bollé, P. Kozłowski

Publication date: 15 August 2002

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

Abstract: We study supervised learning and generalisation in coupled perceptrons trained on-line using two learning scenarios. In the first scenario the teacher and the student are independent networks and both are represented by an Ashkin-Teller perceptron. In the second scenario the student and the teacher are simple perceptrons but are coupled by an Ashkin-Teller type four-neuron interaction term. Expressions for the generalisation error and the learning curves are derived for various learning algorithms. The analytic results find excellent confirmation in numerical simulations.

Full work available at URL: https://arxiv.org/abs/cond-mat/0111493

Recommendations

• scientific article; zbMATH DE number 1329967
• On-line learning in the Ising perceptron.
• Generalization from educated teachers
• On-line learning with restricted training sets: An exactly solvable case

zbMATH Keywords

neural networksAshkin-Teller perceptronon-line learning processes

Mathematics Subject Classification ID

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

Cited In (10)

• On-line learning in the Ising perceptron.
• On-line learning of non-monotonic rules by simple perceptron
• On-line learning through simple perceptron learning with a margin
• Generalization from educated teachers
• On-Line Learning in Neural Networks
• Ensemble Learning of Linear Perceptrons: On-Line Learning Theory
• Title not available (Why is that?)
• On-line learning in parity machines
• Online learning dynamics of multilayer perceptrons with unidentifiable parameters
• Title not available (Why is that?)

This page was built for publication: On-line learning and generalization in coupled perceptrons

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4545296)