ML Anthology

Is Active Learning Always Beneficial? (Student Abstract)

Anna Kravchenko, Rhodri Cusack
AAAI 2021 pp. 15819-15820
doi:10.1609/AAAI.V35I18.17906 /aaai/2021/kravchenko2021aaai-active/

Abstract

This study highlights the limitations of automated curriculum learning, which may not be a viable strategy for tasks in which the benefits of the chosen curriculum are not apparent until much later. Using a simple convolutional network and a two-task training regime, we show that in some cases a network is not able to derive an optimal learning strategy using only the data available during a single training run.

PDF AAAI Semantic Scholar

Cite

Text

Kravchenko and Cusack. "Is Active Learning Always Beneficial? (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17906

Markdown

[Kravchenko and Cusack. "Is Active Learning Always Beneficial? (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/kravchenko2021aaai-active/) doi:10.1609/AAAI.V35I18.17906

BibTeX

@inproceedings{kravchenko2021aaai-active,
  title     = {{Is Active Learning Always Beneficial? (Student Abstract)}},
  author    = {Kravchenko, Anna and Cusack, Rhodri},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15819-15820},
  doi       = {10.1609/AAAI.V35I18.17906},
  url       = {https://mlanthology.org/aaai/2021/kravchenko2021aaai-active/}
}