Sciweavers

6709 search results - page 404 / 1342
» Impacting the Learning Experience
Sort
View
ICIP
2006
IEEE
16 years 9 months ago
Precision-Oriented Active Selection for Interactive Image Retrieval
Active learning methods have been considered with an increased interest in the content-based image retrieval (CBIR) community. Those methods used to be based on classical classifi...
Philippe Henri Gosselin, Matthieu Cord
ICML
2009
IEEE
16 years 8 months ago
Approximate inference for planning in stochastic relational worlds
Relational world models that can be learned from experience in stochastic domains have received significant attention recently. However, efficient planning using these models rema...
Tobias Lang, Marc Toussaint
ICML
2008
IEEE
16 years 8 months ago
Cost-sensitive multi-class classification from probability estimates
For two-class classification, it is common to classify by setting a threshold on class probability estimates, where the threshold is determined by ROC curve analysis. An analog fo...
Deirdre B. O'Brien, Maya R. Gupta, Robert M. Gray
ICML
2006
IEEE
16 years 8 months ago
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...
Alex Graves, Faustino J. Gomez, Jürgen Schmid...
ICML
2005
IEEE
16 years 8 months ago
Predicting relative performance of classifiers from samples
This paper is concerned with the problem of predicting relative performance of classification algorithms. It focusses on methods that use results on small samples and discusses th...
Rui Leite, Pavel Brazdil