NEURAL NETWORK DEVICE FOR EVOLVING APPROPRIATE CONNECTIONS

A system and method for evolving appropriate connections in feedforward topological networks (Fig. 1) illustrates an exemplary flow diagram of a method for evolving appropriate connections in a neural network device according to an aspect of the present invention. Initially, weight changes induced by each particular training sample or pattern are calculated using, for example, a conventional network training rule such as Hebb or backpropagation (step 101). Next, a ratio of the weight changes for existing connections to incipient connections ("K" ratio) is calculated (step 103). If this K ratio exceeds a specified threshold, weight changes are implemented (step 105), in which existing weights are increased by (1-E)x(total weight change of existing connections), where E is a network-wide parameter. The remaining amount (E)x(total weight change of existing connections) is added to form neighboring connections (step 107). It is to be noted that if neighboring connections are not yet in existence (i.e, they are incipient connections), they can be created by this mutation rule; however, whether such new connections are created depends on the size of the weight increase computed in step 101, together with the magnitude of E. After cycling through a training set, connections that are weak (e.g., weaker than a specified threshold) are deleted (step 109). Following step 109, the system returns to step 101. Advantageously, a system and method according to the present invention allows a combination of the advantages of fully connected networks and of sparse networks and reduces the number of calculations that must be done, since only the calculations corresponding to the existing connections and their neighbors need be determined. L'invention concerne un système et un procédé permettant de développer des connexions appropriées dans des réseaux topologiques sans rétroaction. La Fig. 1 représente un organigramme d'un procédé permettant de développer des connexions appropriées dans un dispositif de réseau neuronal selon la présente invention. Initialement, des changements de poids induits par chaque échantillon d'entraînement particulier ou chaque motif particulier sont calculés au moyen, par exemple, d'une règle d'entraînement de réseau conventionnelle telle que la règle de Hebb ou la règle de rétropropagation (étape 101). Ensuite, un rapport des modifications de poids entre des connexions existantes et des connexions naissantes (rapport "K") est calculé (étape 103). Si