Control of Generalization with a Bi-Objective Sliding Mode Control Algorithm

Marcelo Azevedo CostaAntônio de Pádua BragaBenjamin Rodrigues de MenezesGustavo Guimarães ParmaRoselito de Albuquerque Teixeira

This paper presents a new sliding mode control algorithm that is able to guide the trajectory of a Multi-Layer Perceptron (MLP) within the plane formed by the two objectives: training set error and norm of the weight vectors. The results show that the neural networks obtained are able to generate the Pareto set, from which a model with the smallest validation error is selected.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: