Proposition of two evolutionist approaches - genetic algorithm and neural network - to solve CSP

Within the framework of the constraint satisfaction problem (CSP) resolution, we propose two methods based on the principle of evolutionist algorithms. The resolution is carried out under two tests. Initially, we present a genetic algorithm, which uses original operators, based on personal heuristic...

Full description

Saved in:
Bibliographic Details
Main Authors: Hamissi, S., Siyahia, N., Babes, M.
Format: Conference Proceeding
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Concrete
Explosions
Genetic algorithms
Neural networks
Space exploration
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Within the framework of the constraint satisfaction problem (CSP) resolution, we propose two methods based on the principle of evolutionist algorithms. The resolution is carried out under two tests. Initially, we present a genetic algorithm, which uses original operators, based on personal heuristic, and we propose, thereafter, an algorithm based on the conception of a basic neural network able to solve some instantiations of the CSP. The results obtained are very encouraging. Indeed, if the search space is of significant size and if it is difficult to isolate an acceptable solution, which is the case of the CSPs, the use of the proposed heuristics is rather promising.
DOI:10.1109/GMAG.2003.1219679