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

DOI10.1088/0305-4470/26/15/025zbMath0793.92003MaRDI QIDQ4291664

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

capacity; single-layer perceptron; neural network training algorithms; input neuron states; linearly separable solution; output neuron state; random selection of input-output relations; set of binary vectors

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

92B20: Neural networks for/in biological studies, artificial life and related topics

82C32: Neural nets applied to problems in time-dependent statistical mechanics