Tags: deep learning* + classification* + bert*

0 bookmark(s) - Sort by: Date ↓ / Title /

  1. BEAL is a deep active learning method that uses Bayesian deep learning with dropout to infer the model’s posterior predictive distribution and introduces an expected confidence-based acquisition function to select uncertain samples. Experiments show that BEAL outperforms other active learning methods, requiring fewer labeled samples for efficient training.
  2. 2021-09-25 Tags: , , , by klotz
  3. 2020-08-03 Tags: , , , , by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0 SemanticScuttle - klotz.me: tagged with "deep learning+classification+bert"

About - Propulsed by SemanticScuttle