4544 search results - page 467 / 909 » Reinforcement Learning with Time |
204
click to vote
ICMCS
2009
IEEE
15 years 4 months ago
2009
IEEE
In the H.264/AVC coding standard, motion estimation (ME) is allowed to use multiple reference frames to make full use of reducing temporal redundancy in a video sequence. Although...
223
click to vote
JMLR
2010
15 years 1 months ago
2010
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
223
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
We propose a kernelized maximal-figure-of-merit (MFoM) learning approach to efficiently training a nonlinear model using subspace distance minimization. In particular, a fixed,...
183
click to vote
AGI
2011
14 years 10 months ago
2011
We present an architectural approach to learning problem solving skills from demonstration, using internal models to represent problem-solving operational knowledge. Internal forwa...
186
click to vote
AAAI
2011
14 years 7 months ago
2011
We propose a fast batch learning method for linearchain Conditional Random Fields (CRFs) based on Newton-CG methods. Newton-CG methods are a variant of Newton method for high-dime...