Parallel Training of a Back-Propagation Neural Network Using CUDA

• Published in: 2010 International Conference on Machine Learning and Applications pp. 307 - 312
• Main Authors: Sierra-Canto, X, Madera-Ramirez, F, Uc-Cetina, V
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2010
• Subjects: Artificial neural networks; back-propagation; CUDA; Distance measurement; Graphics processing unit; Instruction sets; Kernel; neural networks; Neurons; Training

The Artificial Neural Networks (ANN) training represents a time-consuming process in machine learning systems. In this work we provide an implementation of the back-propagation algorithm on CUDA, a parallel computing architecture developed by NVIDIA. Using CUBLAS, a CUDA implementation of the Basic...