Marcelo Azevedo Costa,  Antônio de Pádua Braga,  Benjamin Rodrigues de Menezes. 

This paper presents methods to improve generalization of Multi-Layer Perceptron (MLP) by pruning the original topology without loss in performance. Topology information and validation sets are used. The results show that these techniques are able to choose a minimum network topology and to simplify trained networks.

http://csdl.computer.org/comp/proceedings/sbrn/2002/1709/00/17090049abs.htm

Processando consulta.