High-performance simulation of neural networks

Author

Rademacher, Timothy J. ; Lumpp, James E., Jr.

Author_Institution

Lexmark Int. Inc., Lexington, KY, USA

Volume

3

fYear

1997

fDate

1-8 Feb 1997

Firstpage

401

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

Keywords

backpropagation; feedforward neural nets; neural net architecture; parallel architectures; virtual machines; artificial neural networks; backpropagation algorithm; bit parallelism; high-performance simulation; layer parallelism; multilayer feedforward network; nested loops; node parallelism; parallel simulation methods; parallel systems; training; weight parallelism; weights updating; Artificial neural networks; Biological neural networks; Brain modeling; Computational modeling; Computer networks; Computer simulation; Feedforward systems; Humans; Neural networks; Workstations;

fLanguage

English

Publisher

ieee

Conference_Titel

Aerospace Conference, 1997. Proceedings., IEEE

Conference_Location

Snowmass at Aspen, CO

Print_ISBN

0-7803-3741-7

Type

conf

DOI

10.1109/AERO.1997.574894

Filename

574894