Part of Neural Information Processing Systems 0 (NIPS 1987)
J. Bernasconi
We
investigate the behavior of different learning algorithms
for networks of neuron-like units. As test cases we use simple pat(cid:173) tern association problems, such as the XOR-problem and symmetry de(cid:173) tection problems. The algorithms considered are either versions of the Boltzmann machine learning rule or based on the backpropagation of errors. We also propose and analyze a generalized delta rule for linear threshold units. We find that the performance of a given learning algorithm depends strongly on the type of units used. In particular, we observe that networks with ±1 units quite generally exhibit a significantly better learning behavior than the correspon(cid:173) ding 0,1 versions. We also demonstrate that an adaption of the weight-structure to the symmetries of the problem can lead to a drastic increase in learning speed.