2295 search results - page 295 / 459 » Learning Overcomplete Representations |
102
Voted
ALT
2010
Springer
15 years 4 months ago
2010
Springer
We are studying long term sequence prediction (forecasting). We approach this by investigating criteria for choosing a compact useful state representation. The state is supposed t...
130
Voted
EDM
2008
15 years 4 months ago
2008
This paper discusses our approach to building models and analyzing student behaviors in different versions of our learning by teaching environment where students learn by teaching ...
123
click to vote
EMNLP
2008
15 years 4 months ago
2008
Machine learning approaches to coreference resolution are typically supervised, and require expensive labeled data. Some unsupervised approaches have been proposed (e.g., Haghighi...
138
Voted
UAI
2008
15 years 4 months ago
2008
Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinfor...
NIPS
2001
15 years 4 months ago
2001
Unsupervised learning algorithms have been derived for several statistical models of English grammar, but their computational complexity makes applying them to large data sets int...