202 search results - page 18 / 41 » Privacy-preservation for gradient descent methods |
ML
2002
ACM
14 years 11 months ago
2002
ACM
The problem of automatically tuning multiple parameters for pattern recognition Support Vector Machines (SVMs) is considered. This is done by minimizing some estimates of the gener...
109
click to vote
CVIU
2007
14 years 11 months ago
2007
Tracking articulated structures like a hand or body within a reasonable time is challenging because of the high dimensionality of the state space. Recently, a new optimization met...
KDD
2005
ACM
15 years 12 months ago
2005
ACM
Several authors have suggested viewing boosting as a gradient descent search for a good fit in function space. At each iteration observations are re-weighted using the gradient of...
107
click to vote
DAGM
2008
Springer
15 years 1 months ago
2008
Springer
Abstract. Virtually all variational methods for motion estimation regularize the gradient of the flow field, which introduces a bias towards piecewise constant motions in weakly te...
ICASSP
2011
IEEE
14 years 3 months ago
2011
IEEE
We describe a new approach for phoneme recognition which aims at minimizing the phoneme error rate. Building on structured prediction techniques, we formulate the phoneme recogniz...