360 search results - page 22 / 72 » Combining Learned Discrete and Continuous Action Models |
143
click to vote
ICASSP
2011
IEEE
14 years 8 months ago
2011
IEEE
Current hidden Markov acoustic modeling for large vocabulary continuous speech recognition (LVCSR) relies on the availability of abundant labeled transcriptions. Given that speech...
121
click to vote
AAAI
2007
15 years 6 months ago
2007
We describe how a physical robot can learn about objects from its own autonomous experience in the continuous world. The robot identifies statistical regularities that allow it t...
138
click to vote
CVPR
2010
IEEE
16 years 12 days ago
2010
IEEE
A central problem in the analysis of motion capture (Mo-
Cap) data is how to decompose motion sequences into primitives.
Ideally, a description in terms of primitives should
fac...
147
click to vote
WSC
2000
15 years 5 months ago
2000
Many artificial intelligence techniques rely on the notion ate" as an abstraction of the actual state of the nd an "operator" as an abstraction of the actions that ...
123
click to vote
ICALP
2005
Springer
15 years 9 months ago
2005
Springer
In this paper we initiate the study of discrete random variables over domains. Our work is inspired by work of Daniele Varacca, who devised indexed valuations as models of probabi...