Sciweavers

47 search results - page 5 / 10
» Meta-learning for Fast Incremental Learning
Sort
View
ACL
2011
13 years 5 days ago
Jointly Learning to Extract and Compress
We learn a joint model of sentence extraction and compression for multi-document summarization. Our model scores candidate summaries according to a combined linear model whose fea...
Taylor Berg-Kirkpatrick, Dan Gillick, Dan Klein
ECCV
2008
Springer
14 years 10 months ago
Keypoint Signatures for Fast Learning and Recognition
Abstract. Statistical learning techniques have been used to dramatically speed-up keypoint matching by training a classifier to recognize a specific set of keypoints. However, the ...
Michael Calonder, Vincent Lepetit, Pascal Fua
ADMA
2010
Springer
271views Data Mining» more  ADMA 2010»
13 years 3 months ago
Exploiting Concept Clumping for Efficient Incremental E-Mail Categorization
We introduce a novel approach to incremental e-mail categorization based on identifying and exploiting "clumps" of messages that are classified similarly. Clumping reflec...
Alfred Krzywicki, Wayne Wobcke
CORR
2002
Springer
132views Education» more  CORR 2002»
13 years 8 months ago
Robust Feature Selection by Mutual Information Distributions
Mutual information is widely used in artificial intelligence, in a descriptive way, to measure the stochastic dependence of discrete random variables. In order to address question...
Marco Zaffalon, Marcus Hutter
EUROCAST
2003
Springer
108views Hardware» more  EUROCAST 2003»
14 years 1 months ago
Fast Entropy-Based Nonrigid Registration
Computer vision tasks such as learning, recognition, classification or segmentation applied to spatial data often requires spatial normalization of repeated features and structure...
Eduardo Suárez, Jose Aurelio Santana, Eduar...