Active Learning for Informative Projection Retrieval

AAAI 2015 pp. 4158-4159

doi:10.1609/AAAI.V29I1.9742 /aaai/2015/fiterau2015aaai-active/

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.

PDF AAAI Semantic Scholar

Cite

Text

Fiterau and Dubrawski. "Active Learning for Informative Projection Retrieval." AAAI Conference on Artificial Intelligence, 2015. doi:10.1609/AAAI.V29I1.9742

Markdown

[Fiterau and Dubrawski. "Active Learning for Informative Projection Retrieval." AAAI Conference on Artificial Intelligence, 2015.](https://mlanthology.org/aaai/2015/fiterau2015aaai-active/) doi:10.1609/AAAI.V29I1.9742

BibTeX

@inproceedings{fiterau2015aaai-active,
  title     = {{Active Learning for Informative Projection Retrieval}},
  author    = {Fiterau, Madalina and Dubrawski, Artur},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2015},
  pages     = {4158-4159},
  doi       = {10.1609/AAAI.V29I1.9742},
  url       = {https://mlanthology.org/aaai/2015/fiterau2015aaai-active/}
}