A Study of Random Neural Network Performance for Supervised Learning Tasks in CUDA

Abstract

The Graphics Processing Unit (GPU) have been used for accelerating graphic calculations as well as for developing more general devices. One of the most used parallel platform is Compute Unified Device Architecture (CUDA). This one allows to implement in parallel multiple GPU obtaining a high computational performance. Over the last years, CUDA has been used for the implementation of several parallel distributed systems. At the end of the 80s, it was introduced a stochastic neural network named Random Neural Networks (RNN). The method have been successfully used in the Machine Learning community for solving many learning tasks. In this paper we present the gradient descent algorithm for the RNN model in CUDA. We evaluate the performance of the algorithm on two real benchmark problems about energy sources, and we compare it with the obtained using a classic implementation in C.KeywordsRandom Neural NetworkParallel ComputingCUDAGradient Descent Algorithm