641 search results - page 106 / 129 » Training Methods for Adaptive Boosting of Neural Networks |
112
click to vote
ICANN
2010
Springer
14 years 10 months ago
2010
Springer
Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
ICANN
2011
Springer
14 years 1 months ago
2011
Springer
Currently the most accurate WLAN positioning systems are based on the fingerprinting approach, where a “radio map” is constructed by modeling how the signal strength measureme...
103
Voted
WSC
2007
14 years 12 months ago
2007
Simulation optimization (SO) is the process of finding the optimum design of a system whose performance measure(s) are estimated via simulation. We propose some ideas to improve o...
NCA
2007
IEEE
14 years 9 months ago
2007
IEEE
Learning from imbalanced data occurs frequently in many machine learning applications. One positive example to thousands of negative instances is common in scientific applications...
TSD
2007
Springer
15 years 3 months ago
2007
Springer
The present study proposes an inter-speaker audiovisual synchronization method to decrease the speaker dependency of our direct speech to animation conversion system. Our aim is to...