Sciweavers

311 search results - page 39 / 63
» Gradient Convergence in Gradient methods with Errors
Sort
View
ICCV
2007
IEEE
14 years 1 months ago
Non-Rigid Object Alignment with a Mismatch Template Based on Exhaustive Local Search
Non-rigid object alignment is especially challenging when only a single appearance template is available and target and template images fail to match. Two sources of discrepancy b...
Yang Wang, Simon Lucey, Jeffrey F. Cohn
AMC
2007
154views more  AMC 2007»
13 years 7 months ago
A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training
The particle swarm optimization algorithm was showed to converge rapidly during the initial stages of a global search, but around global optimum, the search process will become ve...
Jing-Ru Zhang, Jun Zhang, Tat-Ming Lok, Michael R....
IWCM
2004
Springer
14 years 28 days ago
Wiener-Optimized Discrete Filters for Differential Motion Estimation
Abstract. Differential motion estimation is based on detecting brightness changes in local image structures. Filters approximating the local gradient are applied to the image seque...
Kai Krajsek, Rudolf Mester
ICASSP
2011
IEEE
12 years 11 months ago
SRF: Matrix completion based on smoothed rank function
In this paper, we address the matrix completion problem and propose a novel algorithm based on a smoothed rank function (SRF) approximation. Among available algorithms like FPCA a...
Hooshang Ghasemi, Mohmmadreza Malek-Mohammadi, Mas...
AE
2005
Springer
14 years 1 months ago
Algorithms (X, sigma, eta): Quasi-random Mutations for Evolution Strategies
Randomization is an efficient tool for global optimization. We here define a method which keeps : – the order 0 of evolutionary algorithms (no gradient) ; – the stochastic as...
Anne Auger, Mohamed Jebalia, Olivier Teytaud