2 search results - page 1 / 1 » Hidden Layer Training via Hessian Matrix Information |
FLAIRS
2004
13 years 8 months ago
2004
The output weight optimization-hidden weight optimization (OWO-HWO) algorithm for training the multilayer perceptron alternately updates the output weights and the hidden weights....
FOCI
2007
IEEE
14 years 1 months ago
2007
IEEE
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...