UPM Institutional Repository

Parallel simulation of character recognition problems using NEUCOMP2


Citation

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

Abstract

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.


Download File

[img]
Preview
PDF (Abstract)
Parallel simulation of character recognition problems using NEUCOMP2.pdf

Download (36kB) | Preview

Additional Metadata

Item Type: Article
Divisions: Faculty of Computer Science and Information Technology
DOI Number: https://doi.org/10.1080/10637199608915605
Publisher: Gordon and Breach Science Publishers
Keywords: Neural network compiler; NEUCOMP2; A shared-memory parallel machine; General purpose simulation tool; Backpropagation; Kohonen; Counterpropagation; ART1 networks; SEQUENT Balance 8000
Depositing User: Nabilah Mustapa
Date Deposited: 17 Jan 2018 03:30
Last Modified: 17 Jan 2018 03:30
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1080/10637199608915605
URI: http://psasir.upm.edu.my/id/eprint/58450
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item