55 search results - page 8 / 11 » Supervised Learning by Training on Aggregate Outputs |
ICCV
2005
IEEE
14 years 10 months ago
2005
IEEE
Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can...
IEAAIE
2005
Springer
14 years 2 months ago
2005
Springer
Prediction is an important task in robot motor control where it is used to gain feedback for a controller. With such a self-generated feedback, which is available before sensor rea...
ENGL
2007
13 years 8 months ago
2007
—“A General Reflex Fuzzy Min-Max Neural Network” (GRFMN) is presented. GRFMN is capable to extract the underlying structure of the data by means of supervised, unsupervised a...
MICAI
2010
Springer
2010
Springer
Combining Neural Networks Based on Dempster-Shafer Theory for Classifying Data with Imperfect Labels
13 years 7 months ago
This paper addresses the supervised learning in which the class membership of training data are subject to uncertainty. This problem is tackled in the framework of the Dempster-Sha...
IJCNN
2006
IEEE
14 years 2 months ago
2006
IEEE
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...