High-performance simulation of neural networks

Timothy J. Rademacher, James E. Lumpp

Research output: Contribution to conferencePaperpeer-review

Abstract

Artificial neural networks have been used for a wide range of problems in a variety of areas. The back-propagation algorithm is frequently used to train the network, but is time consuming when implemented on general-purpose computers. This paper examines methods of simulating back-propagation neural networks on parallel systems to achieve high performance. The training of artificial neural networks consists of updating the weights in several nested loops. Parallel simulation methods may be classified based on which of these loops are executed in parallel. These methods are discussed and example implementations of these methods are described.

Original languageEnglish
Pages401-413
Number of pages13
StatePublished - 1997
EventProceedings of the 1997 IEEE Aerospace Conference. Part 4 (of 4) - Snowmass Village, CO, USA
Duration: Feb 1 1997Feb 2 1997

Conference

ConferenceProceedings of the 1997 IEEE Aerospace Conference. Part 4 (of 4)
CitySnowmass Village, CO, USA
Period2/1/972/2/97

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'High-performance simulation of neural networks'. Together they form a unique fingerprint.

Cite this