Sciweavers

986 search results - page 30 / 198
» Zero-data Learning of New Tasks
Sort
View
CIKM
2008
Springer
14 years 11 months ago
Group-based learning: a boosting approach
This paper points out that many machine learning problems in IR should be and can be formalized in a novel way, referred to as `group-based learning'. In group-based learning...
Weijian Ni, Jun Xu, Hang Li, Yalou Huang
IJCAI
2003
14 years 11 months ago
Understanding the Power of Clause Learning
Efficient implementations of DPLL with the addition of clause learning are the fastest complete satisfiability solvers and can handle many significant real-world problems, such as...
Paul Beame, Henry A. Kautz, Ashish Sabharwal
JGO
2010
117views more  JGO 2010»
14 years 8 months ago
Machine learning problems from optimization perspective
Both optimization and learning play important roles in a system for intelligent tasks. On one hand, we introduce three types of optimization tasks studied in the machine learning l...
Lei Xu
ACL
2012
13 years 5 days ago
Labeling Documents with Timestamps: Learning from their Time Expressions
Temporal reasoners for document understanding typically assume that a document’s creation date is known. Algorithms to ground relative time expressions and order events often re...
Nathanael Chambers
CVPR
2008
IEEE
15 years 11 months ago
On the use of independent tasks for face recognition
We present a method for learning discriminative linear feature extraction using independent tasks. More concretely, given a target classification task, we consider a complementary...
Àgata Lapedriza, David Masip, Jordi Vitri&a...