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

A variation of the well known Levenberg-Marquardt for training neural networks is presented in this work. The algorithm presented restricts the norm of the weigths vector to a preestablished norm value and finds the minimum error solution for that norm value. A range of different norm solutions is generated and the best generalization solution is selected. The results show the efficiency of the algorithm in terms of convergence speed and generalization performance.

http://csdl.computer.org/comp/proceedings/sbrn/2002/1709/00/17090044abs.htm

Processando consulta.