Sciweavers

FLAIRS
2006

Fast Generation of a Sequence of Trained and Validated Feed-Forward Networks

13 years 5 months ago
Fast Generation of a Sequence of Trained and Validated Feed-Forward Networks
In this paper, three approaches are presented for generating and validating sequences of different size neural nets. First, a growing method is given along with several weight initialization methods, and their properties. Then a one pass pruning method is presented which utilizes orthogonal least squares. Based upon this pruning approach, a onepass validation method is discussed. Finally, a training method that combines growing and pruning is described. In several examples, it is shown that the combination approach is superior to growing or pruning alone.
Pramod Lakshmi Narasimha, Walter Delashmit, Michae
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2006
Where FLAIRS
Authors Pramod Lakshmi Narasimha, Walter Delashmit, Michael T. Manry, Jiang Li, F. J. Maldonado
Comments (0)