Authors:
Cruz Enrique Borges Hernández

Abstract:

We experiment with several evolutionary algorithms for solving systems of polynomial equations with real coefficients. As a main difference with previous work, our algorithms can certify the correctness of the so-lutions they provide. This achievement is made possible by incorporating results from the field of numerical analysis to their fitness functions. We have performed an experimental comparison between the various pro-posed algorithms. The results of this comparison show that evolutionary and other local search algorithms can deal with the problem of solving systems of polynomial equations even for systems having many variables and high degree. Our main contribution is a nontrivial fitness function adjusted to the problem to be solved. This function is not based on any heuristics but on the fundamentals of numerical computation.



Proceedings: Proceedings of the International Conference on Evolutionary Computation Theory and Applications
Presented at:

6th International Conference on Evolutionary Computation Theory and Applications (2014)


Year:

2014


Citations:
Citation
Cruz Enrique Borges Hernández. (2014) "A Sharp Fitness Function for the problem of Finding Roots of Polynomial Equations Systems" In Proceedings of the International Conference on Evolutionary Computation Theory and Applications. DOI: 10.13140/2.1.1907.5843.