2924 search results - page 200 / 585 » On the Use of Evidence in Neural Networks |
116
click to vote
INTERSPEECH
2010
14 years 8 months ago
2010
In the paper we present two techniques improving the recognition accuracy of multilayer perceptron neural networks (MLP ANN) by means of adopting Speaker Adaptive Training. The us...
128
click to vote
FLAIRS
2004
15 years 3 months ago
2004
Novelty detection in time series is an important problem with application in different domains such as machine failure detection, fraud detection and auditing. An approach to this...
105
click to vote
BSN
2006
IEEE
15 years 5 months ago
2006
IEEE
System robustness against individual sensor failures is an important concern in multi-sensor networks. Unfortunately, the complexity of using the remaining sensors to interpolate ...
127
click to vote
ICRA
2007
IEEE
15 years 8 months ago
2007
IEEE
Prediction of dynamic features is an important task for determining the manipulation strategies of an object. This paper presents a technique for predicting dynamics of objects re...
116
click to vote
IJCNN
2006
IEEE
15 years 8 months ago
2006
IEEE
Abstract— High-level specification of how the brain represents and categorizes the causes of its sensory input allows to link “what is to be done” (perceptual task) with “...