Sciweavers

68 search results - page 3 / 14
» A stopping criterion for active learning
Sort
View
TNN
2008
79views more  TNN 2008»
13 years 5 months ago
Performing Feature Selection With Multilayer Perceptrons
An experimental study on two decision issues for wrapper feature selection (FS) with multilayer perceptrons and the sequential backward selection (SBS) procedure is presented. The ...
Enrique Romero, Josep M. Sopena
LREC
2008
78views Education» more  LREC 2008»
13 years 7 months ago
Approximating Learning Curves for Active-Learning-Driven Annotation
Active learning (AL) is getting more and more popular as a methodology to considerably reduce the annotation effort when building training material for statistical learning method...
Katrin Tomanek, Udo Hahn
ECML
2004
Springer
13 years 11 months ago
A Boosting Approach to Multiple Instance Learning
In this paper we present a boosting approach to multiple instance learning. As weak hypotheses we use balls (with respect to various metrics) centered at instances of positive bags...
Peter Auer, Ronald Ortner
ICASSP
2009
IEEE
14 years 7 days ago
Maximizing global entropy reduction for active learning in speech recognition
We propose a new active learning algorithm to address the problem of selecting a limited subset of utterances for transcribing from a large amount of unlabeled utterances so that ...
Balakrishnan Varadarajan, Dong Yu, Li Deng, Alex A...
IJCAI
2007
13 years 7 months ago
Optimistic Active-Learning Using Mutual Information
An “active learning system” will sequentially decide which unlabeled instance to label, with the goal of efficiently gathering the information necessary to produce a good cla...
Yuhong Guo, Russell Greiner