3381 search results - page 48 / 677 » LEO - DB2's LEarning Optimizer |
JAIR
2002
13 years 7 months ago
2002
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a di...
ML
2002
ACM
13 years 7 months ago
2002
ACM
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...
CVPR
2000
IEEE
14 years 9 months ago
2000
IEEE
Combining learning with vision techniques in interactive image retrieval has been an active research topic during the past few years. However, existing learning techniques either ...
CDC
2009
IEEE
13 years 5 months ago
2009
IEEE
Abstract-- Local convergence is a limitation of many optimization approaches for multimodal functions. For hybrid model learning, this can mean a compromise in accuracy. We develop...
JMLR
2010
13 years 2 months ago
2010
We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning...