GPU Implementation of a Deep Learning Network for Financial Prediction

Abstract

Machine learning, a branch of artificial intelligence, concerns the construction and study of systems that can learn from data. Neural network is the well-known branch of machine learning & it has been used extensively by researchers for prediction of data and the prediction accuracy depends upon fine tuning of particular financial data. In this paper neural networks have been used for financial prediction and to improve the performance, Graphics Processing Units have been used. They have emerged as important players in the transition of the computing industry from sequential to multi- and many-core computing. In this paper OPENCL and APARAPI have been used in Java to implement & analyse the same.