Re: Neural Networks - A Systematic Introduction
by yaroslavvb on Saturday October 03, 2009 @07:05PM
(#859350)
A curious recent variations is allowing the number of hidden units to be infinite. It was observed that increasing number of hidden units in a two level perceptron reduces the number of local minima encountered during training. Allowing the number of hidden units to be unbounded makes the optimization problem convex http://books.nips.cc/papers/files/nips18/NIPS2005_0583.pdf
[ Parent
| on HN ]
There are no comments on this comment yet.