Parallel simulation of character recognition problems using NEUCOMP2

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 charact...

Full description

Bibliographic Details
Main Authors: Evans, David J., Sulaiman, Md. Nasir
Format: Article
Language:English
Published: Gordon and Breach Science Publishers 1996
Online Access:http://psasir.upm.edu.my/id/eprint/58450/1/Parallel%20simulation%20of%20character%20recognition%20problems%20using%20NEUCOMP2.pdf
_version_ 1825931812796366848
author Evans, David J.
Sulaiman, Md. Nasir
author_facet Evans, David J.
Sulaiman, Md. Nasir
author_sort Evans, David J.
collection UPM
description 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.
first_indexed 2024-03-06T09:32:25Z
format Article
id upm.eprints-58450
institution Universiti Putra Malaysia
language English
last_indexed 2024-03-06T09:32:25Z
publishDate 1996
publisher Gordon and Breach Science Publishers
record_format dspace
spelling upm.eprints-584502018-01-17T03:30:26Z http://psasir.upm.edu.my/id/eprint/58450/ Parallel simulation of character recognition problems using NEUCOMP2 Evans, David J. Sulaiman, Md. Nasir 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. Gordon and Breach Science Publishers 1996 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/58450/1/Parallel%20simulation%20of%20character%20recognition%20problems%20using%20NEUCOMP2.pdf Evans, David J. and Sulaiman, Md. Nasir (1996) Parallel simulation of character recognition problems using NEUCOMP2. Parallel Algorithms and Applications, 10 (1-2). pp. 49-58. ISSN 1744-5760 http://www.tandfonline.com/doi/abs/10.1080/10637199608915605?journalCode=gpaa19 10.1080/10637199608915605
spellingShingle Evans, David J.
Sulaiman, Md. Nasir
Parallel simulation of character recognition problems using NEUCOMP2
title Parallel simulation of character recognition problems using NEUCOMP2
title_full Parallel simulation of character recognition problems using NEUCOMP2
title_fullStr Parallel simulation of character recognition problems using NEUCOMP2
title_full_unstemmed Parallel simulation of character recognition problems using NEUCOMP2
title_short Parallel simulation of character recognition problems using NEUCOMP2
title_sort parallel simulation of character recognition problems using neucomp2
url http://psasir.upm.edu.my/id/eprint/58450/1/Parallel%20simulation%20of%20character%20recognition%20problems%20using%20NEUCOMP2.pdf
work_keys_str_mv AT evansdavidj parallelsimulationofcharacterrecognitionproblemsusingneucomp2
AT sulaimanmdnasir parallelsimulationofcharacterrecognitionproblemsusingneucomp2