Capacity of the single-layer perceptron and minimal trajectory training algorithms

DOI10.1088/0305-4470/26/15/025MaRDI QIDQ4291664zbMATH OpenOpenAlexFDO

Authors David Saad

Publication date 26 July 1994

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

Full work available at URL https://doi.org/10.1088/0305-4470/26/15/025

zbMATH Keywords

capacityinput neuron stateslinearly separable solutionneural network training algorithmsoutput neuron staterandom selection of input-output relationsset of binary vectorssingle-layer perceptron

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Training a perceptron by a bit sequence: storage capacity
• On the performance of single-layered neural networks
• Bounds on the learning capacity of some multi-layer networks
• Storage capacity of a constructive learning algorithm

Cited in

(9)

• On the performance of single-layered neural networks
• An empirical comparison for the performance of single-layer algorithms for training threshold logic units
• scientific article; zbMATH DE number 4206031 (Why is no real title available?)
• scientific article; zbMATH DE number 1301660 (Why is no real title available?)
• Training a perceptron by a bit sequence: storage capacity
• Storage capacity of a constructive learning algorithm
• Capacity of the covariance perceptron
• Algorithmic Learning Theory
• The construction of minimal multilayered perceptrons: A case study for sorting

This page was built for publication: Capacity of the single-layer perceptron and minimal trajectory training algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4291664)