Sciweavers

AMAI
2002
Springer
13 years 11 months ago
Minimizing Output Error in Multi-Layer Perceptrons
act It is well-established that a multi-layer perceptron (MLP) with a single hidden layer of N neurons and an activation function bounded by zero at negative infinity and one at in...
Jonathan P. Bernick
NIPS
1997
14 years 23 days ago
Learning Human-like Knowledge by Singular Value Decomposition: A Progress Report
Singular value decomposition (SVD) can be viewed as a method for unsupervised training of a network that associates two classes of events reciprocally by linear connections throug...
Thomas K. Landauer, Darrell Laham, Peter W. Foltz
ESANN
2001
14 years 25 days ago
Penalized least squares, model selection, convex hull classes and neural nets
We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
Gerald H. L. Cheang, Andrew R. Barron