Sciweavers

1782 search results - page 21 / 357
» Learning in Parallel Universes
Sort
View
ICASSP
2011
IEEE
12 years 10 months ago
USPACOR: Universal sparsity-controlling outlier rejection
The recent upsurge of research toward compressive sampling and parsimonious signal representations hinges on signals being sparse, either naturally, or, after projecting them on a...
Georgios B. Giannakis, Gonzalo Mateos, Shahrokh Fa...
SEAL
2010
Springer
13 years 4 months ago
A Parallel Algorithm for Solving Large Convex Minimax Problems
Ramnik Arora, Utkarsh Upadhyay, Rupesh Tulshyan, J...
TREC
2004
13 years 8 months ago
Columbia University in the Novelty Track at TREC 2004
Our system for the Novelty Track at TREC 2004 looks beyond sentence boundaries as well as within sentences to identify novel, nonduplicative passages. It tries to identify text sp...
Barry Schiffman, Kathleen McKeown
TREC
2007
13 years 8 months ago
FUB, IASI-CNR and University of Tor Vergata at TREC 2007 Blog Track
We present a fully automatic and weighted dictionary to be used in topical opinion retrieval. We also define a simple topical opinion retrieval function that is free from paramete...
Gianni Amati, Edgardo Ambrosi, Marco Bianchi, Carl...
NECO
2008
146views more  NECO 2008»
13 years 6 months ago
Deep, Narrow Sigmoid Belief Networks Are Universal Approximators
In this paper we show that exponentially deep belief networks [3, 7, 4] can approximate any distribution over binary vectors to arbitrary accuracy, even when the width of each lay...
Ilya Sutskever, Geoffrey E. Hinton