986 search results - page 62 / 198 » Zero-data Learning of New Tasks |
136
Voted
AAAI
1998
15 years 5 months ago
1998
The World Wide Web is a vast source of information accessible to computers, but understandable only to humans. The goal of the research described here is to automatically create a...
148
Voted
INTERSPEECH
2010
14 years 10 months ago
2010
In this paper, we propose a novel boosted mixture learning (BML) framework for Gaussian mixture HMMs in speech recognition. BML is an incremental method to learn mixture models fo...
140
Voted
GECCO
2010
Springer
15 years 7 months ago
2010
Springer
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
170
Voted
CVPR
2005
IEEE
15 years 5 months ago
2005
IEEE
The segmentation of anatomical structures has been traditionally formulated as a perceptual grouping task, and solved through clustering and variational approaches. However, such ...
179
Voted
ML
2002
ACM
15 years 3 months ago
2002
ACM
We present a general approach to model selection and regularization that exploits unlabeled data to adaptively control hypothesis complexity in supervised learning tasks. The idea ...