2924 search results - page 464 / 585 » On the Use of Evidence in Neural Networks |
109
Voted
IJCNN
2006
IEEE
15 years 7 months ago
2006
IEEE
—Recognizing human emotions from partial facial features is quite hard to achieve reasonable accuracy. In this paper, we propose to use a tree structure representation to simulat...
122
Voted
IJCNN
2006
IEEE
15 years 7 months ago
2006
IEEE
Abstract— While the model parameters of many kernel learning methods are given by the solution of a convex optimisation problem, the selection of good values for the kernel and r...
120
click to vote
IJCNN
2006
IEEE
15 years 7 months ago
2006
IEEE
— A heuristic is proposed to address free parameter selection for Support Vector Machines, with the goals of improving generalization performance and providing greater insensitiv...
154
click to vote
IJCNN
2006
IEEE
15 years 7 months ago
2006
IEEE
— Recent work has revealed a close connection between certain information theoretic divergence measures and properties of Mercer kernel feature spaces. Specifically, it has been...
152
click to vote
ICANN
2005
Springer
15 years 7 months ago
2005
Springer
Small mobile robots typically have little on-board processing power for time-consuming vision algorithms. Here we show how they can quickly extract very dense yet highly useful inf...