During the last decade Computational Intelligent methods have been employed to address problems arising in the field of Biomedicine. Artificial Neural Networks constitute one of the most widely used Computational Intelligence methods. The supervised training of Artificial Neural Networks amounts to the global minimization of the network error function. Memetic Algorithms (MAs) comprise a family of population– based, heuristic, search algorithms designed to perform global optimization. MAs have been successfully applied in difficult optimization problems with considerable success. In this contribution, we propose a Memetic Algorithm as a neural network training method. The performance of the proposed algorithm is evaluated on problems from the field of Biomedicine.
[1]
Singiresu S. Rao,et al.
Optimization Theory and Applications
,
1980,
IEEE Transactions on Systems, Man, and Cybernetics.
[2]
Lutz Prechelt,et al.
PROBEN 1 - a set of benchmarks and benchmarking rules for neural network training algorithms
,
1994
.
[3]
R. Storn,et al.
Differential Evolution - A simple and efficient adaptive scheme for global optimization over continuous spaces
,
2004
.
[4]
Riccardo Poli,et al.
New ideas in optimization
,
1999
.
[5]
Michael N. Vrahatis,et al.
Memetic Algorithms for Neural Network Training in Bioinformatics
,
2004
.