Implementation of neural network backpropagation in CUDA

Jinfeng Liu, Lei Guo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Training a multilayer Neural Network with Backpropagation algorithm is usually a very time consuming processing. In this paper, we propose an approach which uses CUDA programming model and exploits the computing power of Graphic Processing Units (GPUs) to accelerate the Backpropagation process. Experiments show that this method can achieve up to 7 times of speedup over the CPU counterpart.

Original languageEnglish
Title of host publicationIntelligence Computation and Evolutionary Computation - Results of 2012 International Conference of Intelligence Computation and Evolutionary Computation, ICEC 2012
PublisherSpringer Verlag
Pages1021-1027
Number of pages7
ISBN (Print)9783642316555
DOIs
StatePublished - 2013
Event2012 International Conference of Intelligence Computation and Evolutionary Computation, ICEC 2012 - Wuhan, China
Duration: 7 Jul 20127 Jul 2012

Publication series

NameAdvances in Intelligent Systems and Computing
Volume180 AISC
ISSN (Print)2194-5357

Conference

Conference2012 International Conference of Intelligence Computation and Evolutionary Computation, ICEC 2012
Country/TerritoryChina
CityWuhan
Period7/07/127/07/12

Keywords

  • Backpropagation
  • CUDA
  • GPU
  • Neural Network

Fingerprint

Dive into the research topics of 'Implementation of neural network backpropagation in CUDA'. Together they form a unique fingerprint.

Cite this