Performance of a Stochastic Net

STOCHASTIC nets have been proposed by several authors1–3 as models of cognitive activity. So far, these have been dominated by heuristic constraints designed to show some analogy with the nervous system or merely for ease of computation. An adequate mathematical theory has, as was recognized by Uttley4, to show how such a device can learn relations.

[1]  J. Tukey,et al.  Multiple-Factor Analysis , 1947 .

[2]  Max V. Mathews,et al.  A linear coding for transmitting a set of correlated signals , 1956, IRE Trans. Inf. Theory.

[3]  R. L. Beurle.  Properties of a mass of cells capable of regenerating pulses , 1956, Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences.

[4]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[5]  John von Neumann,et al.  The Computer and the Brain , 1960 .