Multicore and GPU Parallelization of Neural Networks for Face Recognition
Training of Artificial Neural Networks for large data sets is a time consuming task. Various approaches have been proposed to reduce the efforts, many of them by applying parallelization techniques. In this paper we develop and analyze two novel parallel training approaches for Backpropagation neural networks for face recognition. We focus on two specific parallelization environments, using on the one hand OpenMP on a conventional multithreaded CPU and CUDA on a GPU. Based on our findings we give guidelines for the effcient parallelization of Backpropagation neural networks on multicore and GPU architectures. Additionally, we present a traversal method finding the best combination of learning rate and momentum term by varying the number of hidden neurons supporting the parallelization efforts.
Top- Huqqani, Altaf
- Schikuta, Erich
- Yea, Sicen
- Chena, Peng
Category |
Paper in Conference Proceedings or in Workshop Proceedings (Full Paper in Proceedings) |
Event Title |
International Conference on Computational Science, ICCS |
Divisions |
Workflow Systems and Technology |
Subjects |
Kuenstliche Intelligenz Computergraphik Parallele Datenverarbeitung |
Event Location |
Barcelona, Spain |
Event Type |
Conference |
Event Dates |
5. - 7. June |
Series Name |
Procedia Computer Science |
Publisher |
Elsevier |
Page Range |
pp. 349-358 |
Date |
June 2013 |
Official URL |
http://dx.doi.org/10.1016/j.procs.2013.05.198 |
Export |