750 search results - page 88 / 150 » Learning SVMs from Sloppily Labeled Data |
NIPS
2008
13 years 10 months ago
2008
We introduce a framework for actively learning visual categories from a mixture of weakly and strongly labeled image examples. We propose to allow the categorylearner to strategic...
KDD
2002
ACM
14 years 9 months ago
2002
ACM
In this paper, we present a new co-training strategy that makes use of unlabelled data. It trains two predictors in parallel, with each predictor labelling the unlabelled data for...
ICML
2010
IEEE
13 years 10 months ago
2010
IEEE
We address the problem of evaluating the risk of a given model accurately at minimal labeling costs. This problem occurs in situations in which risk estimates cannot be obtained f...
ISWC
2006
IEEE
14 years 3 months ago
2006
IEEE
We present an approach to activity discovery, the unsupervised identification and modeling of human actions embedded in a larger sensor stream. Activity discovery can be seen as ...
ICML
2008
IEEE
2008
IEEE
A unified architecture for natural language processing: deep neural networks with multitask learning
14 years 10 months ago
We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity...