Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning

@article{Pang2018MetaLearningTA,
  title={Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning},
  author={Kunkun Pang and Mingzhi Dong and Yang Wu and Timothy M. Hospedales},
  journal={CoRR},
  year={2018},
  volume={abs/1806.04798}
}
Active learning (AL) aims to enable training high performance classifiers with low annotation cost by predicting which subset of unlabelled instances would be most beneficial to label. The importance of AL has motivated extensive research, proposing a wide variety of manually designed AL algorithms with diverse theoretical and intuitive motivations. In… CONTINUE READING