The new nondeterministic model of sigmoidal neural network

A new way to derive an artificial neural network of sigmoidal neurons from a nondeterministic model of logic circuits is presented. It can be used to classify the behavior of biological neural nets and of methods for synthesising fuzzy integrated-circuit chips. Some results of a computer simulation of a sigmoidal network from logic elements are examined. The most promising feature of the proposed approach is its consideration of networks which can be determined by some general rules of growth. With these rules, only the region where the network connections needs to be known, i.e. exact addresses for connections are not required.<
>