AI summary

This paper explores learning models in random nets, particularly focusing on operant reinforcement and complex conditioning. It analyzes pattern recognition using Bayes's rule and discusses optimizing techniques like hill-climbing and variational optimization. The paper uses cognitive and computational demons and concludes that random nets can be useful.

Abstract

THE general nature of the problem is that an organism must learn to make the 'right', or appropriate, response to its inputs. Typically, the inputs are large amounts of data, so that the machine must learn to recognize the similarities between different inputs which call for the same response, contrasted with the distinctions that call for different responses. The particular machines we are concerned with are random nets. A random net is a large set of similar and simply-acting elements whose attributes and interactive connections may be randomly established. The extent to which randomness is a part of setting up or maintaining a net varies in the literature, and more recent accounts tend to minimize the use of randomness. Some of the units are usually designated input, and some output units. The units themselves are termed neurons or cells. The underlying reason for the interest in random nets is the belief that if 'right' responses are rewarded by some 'reinforcement', perhaps of the contributing connections, and 'wrong' ones discouraged, then the net as a whole will organize itself so as to tend to make only right responses, even when they are very complicated and abstruse. The underlying and, to us, over optimistic hope is that the complexities of connection and function of a random net, and especially its randomness, may enable it to solve problems that are really hard.