1127 search results - page 146 / 226 » Improving Data Locality by Chunking |
128
click to vote
CF
2005
ACM
15 years 6 months ago
2005
ACM
In this paper, we consider alternate ways of storing a sparse matrix and their effect on computational speed. They involve keeping both the indices and the non-zero elements in t...
115
click to vote
ACL
2008
15 years 5 months ago
2008
We apply the hypothesis of "One Sense Per Discourse" (Yarowsky, 1995) to information extraction (IE), and extend the scope of "discourse" from one single docum...
143
click to vote
APVIS
2010
15 years 5 months ago
2010
This paper introduces a new design to allow interactive, direct manipulation of volume data on volumetrically rendered images. We present an adaptive volume proxy mesh which serve...
137
Voted
ICML
2010
IEEE
15 years 5 months ago
2010
IEEE
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
139
click to vote
ICML
2010
IEEE
15 years 5 months ago
2010
IEEE
The structure of a Markov network is typically learned using top-down search. At each step, the search specializes a feature by conjoining it to the variable or feature that most ...