PARALLEL SIMULATION OF CHARACTER RECOGNITION PROBLEMS USING NEUCOMP2
作者:
D. J. EVANS,
M. N. SULAIMAN,
期刊:
Parallel Algorithms and Applications
(Taylor Available online 1996)
卷期:
Volume 10,
issue 1-2
页码: 49-58
ISSN:1063-7192
年代: 1996
DOI:10.1080/10637199608915605
出版商: Taylor & Francis Group
关键词: Neural Network Compiler;NEUCOMP2;a shared-memory parallel machine;generalpurpose simulation tool;backpropagation;Kohonen;countcrpropagation;ART1 networks;SEQUENT Balance 8000
数据来源: Taylor
摘要:
NEUCOMP2 is a parallel Neural Network Compiler for a shared-memory parallel machine. It compiles a program written as a list of mathematical specifications of Neural Network (NN) models and then translates it into a chosen target program which contains parallel codes. Performance results for character recognition problems on popular NN models are presented. The models are the backpropagation, Kohonen, Counterpropagation and ART1 network models. NEUCOMP2 was developed and run on the SEQUENT Balance 8000 computer system at PARC.
点击下载:
PDF (142KB)
返 回