Sciweavers

986 search results - page 16 / 198
» Zero-data Learning of New Tasks
Sort
View
ICML
2010
IEEE
15 years 28 days ago
Boosting for Regression Transfer
The goal of transfer learning is to improve the learning of a new target concept given knowledge of related source concept(s). We introduce the first boosting-based algorithms for...
David Pardoe, Peter Stone
ATAL
2006
Springer
15 years 3 months ago
Teaching new teammates
Knowledge transfer between expert and novice agents is a challenging problem given that the knowledge representation and learning algorithms used by the novice learner can be fund...
Doran Chakraborty, Sandip Sen
NAACL
2003
15 years 1 months ago
Weakly Supervised Natural Language Learning Without Redundant Views
We investigate single-view algorithms as an alternative to multi-view algorithms for weakly supervised learning for natural language processing tasks without a natural feature spl...
Vincent Ng, Claire Cardie
ICRA
2006
IEEE
149views Robotics» more  ICRA 2006»
15 years 5 months ago
On Learning the Statistical Representation of a Task and Generalizing it to Various Contexts
— This paper presents an architecture for solving generically the problem of extracting the constraints of a given task in a programming by demonstration framework and the problem...
Sylvain Calinon, Florent Guenter, Aude Billard
PAKDD
2010
ACM
151views Data Mining» more  PAKDD 2010»
15 years 4 months ago
Ensemble Learning Based on Multi-Task Class Labels
Abstract. It is well known that diversity among component classifiers is crucial for constructing a strong ensemble. Most existing ensemble methods achieve this goal through resam...
Qing Wang, Liang Zhang