Sciweavers

88 search results - page 11 / 18
» nips 2000
Sort
View
NIPS
2000
13 years 9 months ago
Regularized Winnow Methods
In theory, the Winnow multiplicative update has certain advantages over the Perceptron additive update when there are many irrelevant attributes. Recently, there has been much eff...
Tong Zhang
NIPS
2000
13 years 9 months ago
Improved Output Coding for Classification Using Continuous Relaxation
Output coding is a general method for solving multiclass problems by reducing them to multiple binary classification problems. Previous research on output coding has employed, alm...
Koby Crammer, Yoram Singer
NIPS
2000
13 years 9 months ago
An Information Maximization Approach to Overcomplete and Recurrent Representations
The principle of maximizing mutual information is applied to learning overcomplete and recurrent representations. The underlying model consists of a network of input units driving...
Oren Shriki, Haim Sompolinsky, Daniel D. Lee
NIPS
2000
13 years 9 months ago
Kernel Expansions with Unlabeled Examples
Modern classification applications necessitate supplementing the few available labeled examples with unlabeled examples to improve classification performance. We present a new tra...
Martin Szummer, Tommi Jaakkola
NIPS
2000
13 years 9 months ago
The Kernel Trick for Distances
A method is described which, like the kernel trick in support vector machines (SVMs), lets us generalize distance-based algorithms to operate in feature spaces, usually nonlinearl...
Bernhard Schölkopf