Sciweavers

986 search results - page 19 / 198
» Zero-data Learning of New Tasks
Sort
View
ICCV
2009
IEEE
14 years 7 months ago
Local distance functions: A taxonomy, new algorithms, and an evaluation
We present a taxonomy for local distance functions where most existing algorithms can be regarded as approximations of the geodesic distance defined by a metric tensor. We categor...
Deva Ramanan, Simon Baker
EMNLP
2008
14 years 11 months ago
Online Methods for Multi-Domain Learning and Adaptation
NLP tasks are often domain specific, yet systems can learn behaviors across multiple domains. We develop a new multi-domain online learning framework based on parameter combinatio...
Mark Dredze, Koby Crammer
COLT
2006
Springer
15 years 1 months ago
Online Learning Meets Optimization in the Dual
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
Shai Shalev-Shwartz, Yoram Singer
CVPR
2012
IEEE
13 years 5 days ago
Discriminately decreasing discriminability with learned image filters
In machine learning and computer vision, input signals are often filtered to increase data discriminability. For example, preprocessing face images with Gabor band-pass filters ...
Jacob Whitehill, Javier R. Movellan
SWAP
2008
14 years 11 months ago
Learning SHIQ+log Rules for Ontology Evolution
The definition of new concepts or roles for which extensional knowledge become available can turn out to be necessary to make a DL ontology evolve. In this paper we reformulate thi...
Francesca A. Lisi, Floriana Esposito