986 search results - page 33 / 198 » Zero-data Learning of New Tasks |
ACL
2011
14 years 1 months ago
2011
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid...
180
click to vote
PAKDD
2011
ACM
14 years 3 months ago
2011
ACM
Discovering rare categories and classifying new instances of them is
an important data mining issue in many fields, but fully supervised
learning of a rare class classifier is pr...
ISCI
2002
14 years 9 months ago
2002
Tangible Interfaces for Collaborative Learning Environments (TICLE) explores new ways that multimedia can enhance education without becoming the focus of the educational experienc...
CVPR
2010
IEEE
14 years 10 months ago
2010
IEEE
Transfer learning allows leveraging the knowledge of source domains, available a priori, to help training a classifier for a target domain, where the available data is scarce. Th...
RAS
2010
14 years 8 months ago
2010
Policy Reuse is a reinforcement learning technique that efficiently learns a new policy by using past similar learned policies. The Policy Reuse learner improves its exploration b...