Multicore and GPU Parallelization of Neural Networks for Face Recognition

Multicore and GPU Parallelization of Neural Networks for Face Recognition

Abstract

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.

Grafik Top
Authors
  • Huqqani, Altaf
  • Schikuta, Erich
  • Yea, Sicen
  • Chena, Peng
Grafik Top
Shortfacts
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
Grafik Top