Giters

frkl / active-learning

Active learning for deep learning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

reference paper

pribadihcr opened this issue · comments

commented

Hi @frkl ,

Is there any reference paper for active learning implementation?

Thanks

commented

Vanilla active learning, that is selecting an example with maximum entropy after softmax works the best, resulting in 60%~70% reduction in the amount of training examples. Fancy approaches don't seem to work as well as vanilla active learning. These are empirical results, no formal paper.

commented

Algorithm published as arxiv.org/abs/1711.01732