Performance of Connectionist Learning Algorithms on 2-D SIMD Processor Arrays

Part of Advances in Neural Information Processing Systems 2 (NIPS 1989)

Authors

Fernando Nuñez, José Fortes

Abstract

The mapping of the back-propagation and mean field theory learning algorithms onto a generic 2-D SIMD computer is described. This architecture proves to be very adequate for these applications since efficiencies close to the optimum can be attained. Expressions to find the learning rates are given and then particularized to the DAP array procesor.