Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

September 1994, Vol. 6, No. 5, Pages 916-926
(doi: 10.1162/neco.1994.6.5.916)
© 1994 Massachusetts Institute of Technology
On Langevin Updating in Multilayer Perceptrons
Article PDF (623.42 KB)
Abstract

The Langevin updating rule, in which noise is added to the weights during learning, is presented and shown to improve learning on problems with initially ill-conditioned Hessians. This is particularly important for multilayer perceptrons with many hidden layers, that often have ill-conditioned Hessians. In addition, Manhattan updating is shown to have a similar effect.