A Lamarckian Approach for Neural Network Training |
| |
Authors: | Cortez Paulo Rocha Miguel Neves José |
| |
Affiliation: | (1) Departamento de Informática, Campus de Gualtar, Universidade do Minho, 4710-057 Braga, Portugal. E-mail |
| |
Abstract: | In Nature, living beings improve their adaptation to surrounding environments by means of two main orthogonal processes: evolution and lifetime learning. Within the Artificial Intelligence arena, both mechanisms inspired the development of non-orthodox problem solving tools, namely: Genetic and Evolutionary Algorithms (GEAs) and Artificial Neural Networks (ANNs). In the past, several gradient-based methods have been developed for ANN training, with considerable success. However, in some situations, these may lead to local minima in the error surface. Under
this scenario, the combination of evolution and learning techniques may induce better results, desirably reaching global optima. Comparative tests that were carried out with classification and regression tasks, attest this claim.
This revised version was published online in June 2006 with corrections to the Cover Date. |
| |
Keywords: | feedforward neural networks genetic and evolutionary algorithms hybrid systems lamarckian optimization learning algorithms |
本文献已被 SpringerLink 等数据库收录! |
|