An Efficient Parallel Block Backpropagation Learning Algorithm in Transputer-Based Mesh-Connected Parallel Computers

摘要

Learning process is essential for good perfor- mance when a neural network is applied to a practical applica- tion. The backpropagation algorithm [1] is a well-known learn- ing method widely used in most neural networks. However, since the backpropagation algorithm is time-consuming, much research have been done to speed up the process. The block backprop- agation algorithm, which seems to be more efficient than the backpropagation, is recently proposed by Coetzee in [2]. In this paper, we propose an efficient parallel algorithm for the block backpropagation method and its performance model in mesh- connected parallel computer systems.