Showing papers on "Unsupervised learning published in 1981"
TL;DR: It is demonstrated that a neural network can be described as an automaton and modifications suggested by neurophysiological data are incorporated to improve the speed of convergence.
Abstract: A formal automata-theoretical model for learning neural networks is given. The networks may grow while they learn. It is demonstrated that a neural network can be described as an automaton. Two extreme learning procedures are presented as boundaries for potential learning strategies. An example of a fairly simple automata-theoretical learning procedure is given and modifications suggested by neurophysiological data are incorporated to improve the speed of convergence.
12 citations
TL;DR: A quasi-Bayes approximate learning procedure is proposed that avoids the computational explosion while retaining the flavor of the Bayes solution.
Abstract: The Bayes solution to the unsupervised sequential learning problem induced by a mixture model for the two-class signal versus noise decision problem generates a computational and storage explosion. A quasi-Bayes approximate learning procedure is proposed that avoids the computational explosion while retaining the flavor of the Bayes solution. Convergence is established and efficiency is investigated.
3 citations