Parallel Implementation of Gradient-Based Neural Networks for SVM Training
Leonardo Valente Ferreira, Eugenius Kaszkurewicz, Amit Bhaya · The 2006 IEEE International Joint Conference on Neural Network Proceedings · 2006
This paper presents the implementation of two neural networks for SVM training in parallel computers. The results obtained are compared with two well known packages for SVM training and the parallel implementation shows that the neural network approach can be as accurate as the traditional packages and, since the proposed gradient-based neural networks can be easily parallelized, the proposed approach is scalable and the training times can be considerably reduced.