|
EPIA'03 - 11th Portuguese Conference on Artificial Intelligence
ALEA -- Workshop on Artificial Life and Evolutionary Algorithms
|
Session: December 6, 11:0-12:0, Room B |
Title: |
Evolutionary Approaches for Neural Network Learning |
|
Miguel Rocha, Paulo Cortez and José Neves |
Abstract: |
Several gradient-based methods have been developed for Artificial Neural Network (ANN) training. Still, in some situations, such procedures may lead to local minima, making Evolutionary Algorithms (EAs) a promising alternative.
In this work, EAs using direct representations are
applied to several classification and regression ANN learning tasks. Furthermore, EAs are also combined with local optimization, under the Lamarckian framework. Both strategies are compared with conventional training methods. The results reveal an enhanced performance by a macro-mutation based Lamarckian approach. |
Back to schedule. |