3412 search results - page 352 / 683 » Efficient Reinforcement Learning |
173
click to vote
IJMC
2006
15 years 6 months ago
2006
: M-learning is a rapidly expanding recently domain. Provoked by the fast advances of mobile technologies different applications and systems are developed continuously. Here we add...
155
click to vote
CORR
2000
Springer
15 years 6 months ago
2000
Springer
Adaptive simulated annealing (ASA) is a global optimization algorithm based on an associated proof that the parameter space can be sampled much more efficiently than by using othe...
177
Voted
ACL
2009
15 years 4 months ago
2009
We demonstrate that transformation-based learning can be used to correct noisy speech recognition transcripts in the lecture domain with an average word error rate reduction of 12...
194
click to vote
ATAL
2006
Springer
15 years 10 months ago
2006
Springer
Learning to converge to an efficient, i.e., Pareto-optimal Nash equilibrium of the repeated game is an open problem in multiagent learning. Our goal is to facilitate the learning ...
198
click to vote
KDD
2007
ACM
16 years 7 months ago
2007
ACM
The problem of multimodal data mining in a multimedia database can be addressed as a structured prediction problem where we learn the mapping from an input to the structured and i...