January
2015
Active learning for Informative Projection Recovery
Authors:
Abstract:
We introduce an active learning framework designed to train classification models which use informative projections. Our approach works with the obtained low-dimensional models in finding unlabeled data for annotation by experts. The advantage of our approach is that the labeling effort is expended mainly on samples which benefit models from the considered hypothesis class. This results in an improved learning rate over standard selection criteria for data from the clinical domain.
copied = false, 2000);
">
@conference{Fiterau-2015-121850,
author = {Madalina Fiterau And Artur Dubrawski},
title = {Active learning for Informative Projection Recovery},
booktitle = {Proceedings of 29th AAAI Conference on Artificial Intelligence (AAAI '15)},
year = {2015},
month = {January},
pages = {4158 - 4159},
}
author = {Madalina Fiterau And Artur Dubrawski},
title = {Active learning for Informative Projection Recovery},
booktitle = {Proceedings of 29th AAAI Conference on Artificial Intelligence (AAAI '15)},
year = {2015},
month = {January},
pages = {4158 - 4159},
}