Sciweavers

2 search results - page 1 / 1
» Hidden Layer Training via Hessian Matrix Information
Sort
View
FLAIRS
2004
13 years 5 months ago
Hidden Layer Training via Hessian Matrix Information
The output weight optimization-hidden weight optimization (OWO-HWO) algorithm for training the multilayer perceptron alternately updates the output weights and the hidden weights....
Changhua Yu, Michael T. Manry, Jiang Li
FOCI
2007
IEEE
13 years 10 months ago
Almost All Learning Machines are Singular
— 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...
Sumio Watanabe