A learning rule for very simple universal approximators consisting of a single layer of perceptrons

DOI10.1016/J.NEUNET.2007.12.036MaRDI QIDQ1932023zbMATH OpenOpenAlexWikidataFDO

Authors Peter Auer, Harald Burgsteiner, Wolfgang Maass

Publication date 17 January 2013

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2007.12.036

zbMATH Keywords

committee machineslearning algorithmparallel delta ruleparallel perceptronsreduced communication

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 1928603
• Parallel strategy for optimal learning in perceptrons
• Parallel perceptron learning on a single-channel broadcast communication model
• Learning by parallel Boltzmann machines
• scientific article; zbMATH DE number 822102

Cites work

• Fading memory and the problem of approximating nonlinear operators with Volterra series
• scientific article; zbMATH DE number 50692 (Why is no real title available?)
• scientific article; zbMATH DE number 1314295 (Why is no real title available?)
• scientific article; zbMATH DE number 1928603 (Why is no real title available?)
• scientific article; zbMATH DE number 1392848 (Why is no real title available?)
• scientific article; zbMATH DE number 3231758 (Why is no real title available?)
• scientific article; zbMATH DE number 960160 (Why is no real title available?)
• Large margin classification using the perceptron algorithm
• On the generalization error of fixed combinations of classifiers
• On-line learning in the committee machine
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• The Perceptron: A Model for Brain Functioning. I

Cited in

(10)

• Error-probability noise benefits in threshold neural signal detection
• Parallel strategy for optimal learning in perceptrons
• On-line learning of non-monotonic rules by simple perceptron
• Direct kernel perceptron (DKP): ultra-fast kernel ELM-based classification with non-iterative closed-form weight calculation
• scientific article; zbMATH DE number 1928603 (Why is no real title available?)
• Functional identification of biological neural networks using reservoir adaptation for point processes
• SuperSpike: supervised learning in multilayer spiking neural networks
• Learning from correlated patterns by simple perceptrons
• A global neural network learning machine: coupled integer and fractional calculus operator with an adaptive learning scheme
• On the generalization error of fixed combinations of classifiers

Describes a project that uses

Uses Software

• UCI

This page was built for publication: A learning rule for very simple universal approximators consisting of a single layer of perceptrons

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1932023)