AN OPTIMAL PARALLEL PERCEPTRON LEARNING ALGORITHM FOR A LARGE TRAINING SET

Abstract

In [2], a parallel perceptron learning algorithm on the single-channel broadcast communication model was proposed to speed up the learning of weights of perceptrons [3]. The results in [2] showed that given n training examples, the average speedup is 1.48*n0.91/log n by n processors. Here, we explain how the parallelization may be modified so that it is applicable to any number of processors. Both analytical and experimental results show that the average speedup can reach nearly O(r) by r processors if r is much less than n.