Solving High-Performance Computing Problems Using Distributed Neural Networks with Numerical Methods

Abstract

This paper presents a study on distributed artificial neural networks implemented using wavelet transform-based modular architectures. The research compares the performance of monolithic, vertically partitioned, and horizontally partitioned artificial neural network configurations, with particular focus on computational efficiency and recognition accuracy. Experimental results demonstrate that horizontally partitioned artificial neural networks employing Haar wavelet transforms (2 × 2 kernel) achieve comparable recognition accuracy to monolithic networks (within 1% difference) while significantly reducing processing time. The four-module configuration shows particular promise, with average training time of 0.0754 s per cycle and inference time of 0.0393 s.