AN EXACT LEARNING ALGORITHM FOR AUTOASSOCIATIVE NEURAL NETWORKS WITH BINARY COUPLINGS

Exact solutions for the learning problem of autoassociative networks w ith binary couplings are determined by a new method. The use of a bran ch-and-bound algorithm leads to a substantial saving of computational time compared with complete enumeration. As a result, fully connected networks with up to 40 neurons could be investigated. The network capa city is found to be close to 0.83.