2295 search results - page 116 / 459 » Learning Overcomplete Representations |
106
Voted
ICML
2010
IEEE
15 years 1 months ago
2010
IEEE
This paper studies the problem of learning from ambiguous supervision, focusing on the task of learning semantic correspondences. A learning problem is said to be ambiguously supe...
123
Voted
ML
2011
ACM
14 years 7 months ago
2011
ACM
In the last decade, connectionist models have been proposed that can process structured information directly. These methods, which are based on the use of graphs for the representa...
79
Voted
JMLR
2010
14 years 7 months ago
2010
In this paper, we study the problem of learning a matrix W from a set of linear measurements. Our formulation consists in solving an optimization problem which involves regulariza...
99
Voted
ETS
2006
IEEE
15 years 20 days ago
2006
IEEE
The paper describes an ontology-based framework for bridging learning design and learning object content. In present solutions, researchers have proposed conceptual models and dev...
112
Voted
TLT
2008
15 years 17 days ago
2008
Abstract-- Nowadays, people are in need for continuous learning in order to keep up to date or to be upgraded in their job. An infrastructure for life-long learning requires contin...