387 search results - page 48 / 78 » Improving Reinforcement Learning by Using Case Based Heurist... |
102
click to vote
CSL
2010
Springer
14 years 9 months ago
2010
Springer
This paper describes a statistically motivated framework for performing real-time dialogue state updates and policy learning in a spoken dialogue system. The framework is based on...
128
click to vote
WCE
2008
14 years 11 months ago
2008
Abstract Emotion, personality and individual differences are those effective parameters on human's activities such as learning. People with different personalities show differ...
104
click to vote
CORR
2008
Springer
14 years 9 months ago
2008
Springer
The repeatability and efficiency of a corner detector determines how likely it is to be useful in a real-world application. The repeatability is importand because the same scene vi...
69
Voted
ICCAD
1997
IEEE
15 years 1 months ago
1997
IEEE
An algorithm that remains in use at the core of many partitioning systems is the Kernighan-Lin algorithm and a variant the Fidducia-Matheysses (FM) algorithm. To understand the FM...
CGO
2010
IEEE
15 years 2 months ago
2010
IEEE
Feedback-directed optimization (FDO) is effective in improving application runtime performance, but has not been widely adopted due to the tedious dual-compilation model, the difï...