1227 search results - page 133 / 246 » Learning Rates for Q-Learning |
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resul...
KDD
2008
ACM
15 years 10 months ago
2008
ACM
Classic mixture models assume that the prevalence of the various mixture components is fixed and does not vary over time. This presents problems for applications where the goal is...
105
click to vote
ICIP
2007
IEEE
15 years 4 months ago
2007
IEEE
In this paper, we propose a system identification approach for group activity recognition in traffic surveillance. Statistical shape theory is used to extract features, and then...
ISNN
2007
Springer
15 years 4 months ago
2007
Springer
A neural-based method for source separation in nonlinear mixture is proposed in this paper. A cost function, which consists of the mutual information and partial moments of the out...
MLMI
2007
Springer
15 years 4 months ago
2007
Springer
In this paper, we present a microphone array beamforming approach to blind speech separation. Unlike previous beamforming approaches, our system does not require a-priori knowledge...