Exact solutions for the learning problem of autoassociative networks with binary couplings are determined by a new method. The use of a branch-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 capacity is found to be close to 0.83.
@article{arxiv.cond-mat/9706043,
title = {An exact learning algorithm for autoassociative neural networks with binary couplings},
author = {G. Milde and S. Kobe},
journal= {arXiv preprint arXiv:cond-mat/9706043},
year = {2009}
}