510 search results - page 15 / 102 » Gradient Estimation Revitalized |
134
Voted
ICIP
2010
IEEE
15 years 16 days ago
2010
IEEE
Motion estimation is known to be a non-convex optimization problem. This non-convexity comes from several ambiguities in motion estimation such as the aperture problem, or fast mo...
107
Voted
ICML
2003
IEEE
16 years 3 months ago
2003
IEEE
We show a close relationship between the Expectation - Maximization (EM) algorithm and direct optimization algorithms such as gradientbased methods for parameter learning. We iden...
120
click to vote
ECCV
1994
Springer
16 years 4 months ago
1994
Springer
This paper addresses the problem of computing cues to the three-dimensional structure of surfaces in the world directly from the local structure of the brightness pattern of a bino...
141
Voted
JMLR
2006
15 years 2 months ago
2006
Policy search is a method for approximately solving an optimal control problem by performing a parametric optimization search in a given class of parameterized policies. In order ...
145
Voted
ECML
2005
Springer
15 years 8 months ago
2005
Springer
This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari...