UPM Institutional Repository

Solving optimisation problems using NEUCOMP - a neural network compiler


Citation

Evans, D. J. and Sulaiman, M. N. (1996) Solving optimisation problems using NEUCOMP - a neural network compiler. International Journal of Computer Mathematics, 62 (1-2). pp. 1-21. ISSN 0020-7160; ESSN: 1029-0265

Abstract

NEUCOMP is a Neural Network Compiler that compiles a program written as a list of mathematical specifications of Neural Network (NN) models and then translates it into a chosen target program. A simulation program written in the NEUCOMP language based on selected NN models for Optimisation problems, i.e. Travelling Salesman problem (TSP) is presented. The models are the Continuous Hopfield and Potts-Glass single-layer networks. The compiler is written on the Sequent Balance 8000 machine at PARC. It combines with the graphical package, i.e. Mathematica, to portray some graphical features.


Download File

[img]
Preview
PDF (Abstract)
Solving optimisation problems using NEUCOMP - a neural network compiler.pdf

Download (37kB) | Preview

Additional Metadata

Item Type: Article
Divisions: Universiti Pertanian Malaysia
DOI Number: https://doi.org/10.1080/00207169608804522
Publisher: Taylor & Francis
Keywords: A general-purpose simulation tool; Aequent balance 8000; NEUCOMP; Neural network compiler; Neural network models; Potts-Glass models; The continuous Hopfield; Travelling salesman problem
Depositing User: Nabilah Mustapa
Date Deposited: 13 Apr 2016 04:57
Last Modified: 13 Apr 2016 04:57
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1080/00207169608804522
URI: http://psasir.upm.edu.my/id/eprint/42380
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item