An efficient mapping algorithm of multilayer perceptron on mesh-connected architectures

Abstract

This paper presents a new efficient parallel implementation of neural networks on mesh-connected SRMD machines. A new algorithm to implement the recall and training phases of the multilayer feedforward network with back-error propagation is devised. The developed algorithm is much faster than other known algorithms; it requires O(1) multiplications and O(log N) additions, whereas most others require O(N) multiplications and O(N) additions. The proposed algorithm maximizes parallelism by unfolding the ANN computation to its smallest computational primitives and processes these primitives in parallel.