Time trials on second-order and variable-learning-rate algorithms


Autoria(s): Rohwer, Richard
Contribuinte(s)

Lippmann, R.

Moody, J.

Touretzky, D.

Data(s)

1990

Resumo

The performance of seven minimization algorithms are compared on five neural network problems. These include a variable-step-size algorithm, conjugate gradient, and several methods with explicit analytic or numerical approximations to the Hessian.

Formato

application/pdf

Identificador

http://eprints.aston.ac.uk/342/1/misc91-004.pdf

Rohwer, Richard (1990). Time trials on second-order and variable-learning-rate algorithms. IN: Proceedings of the conference on Advances in neural information processing systems 3. Lippmann, R.; Moody, J. and Touretzky, D. (eds) San Francisco, CA, USA: Morgan Kaufmann.

Publicador

Morgan Kaufmann

Relação

http://eprints.aston.ac.uk/342/

Tipo

Book Section

NonPeerReviewed