Anti-Distillation: Improving Reproducibility of Deep Networks | OpenReview

Anti-Distillation: Improving Reproducibility of Deep Networks | OpenReview

Deep networks have been revolutionary in improving performance of machine learning and artificial intelligence systems. Their high prediction accuracy, however, comes at a price of model...

Keywords: 再現性
Date:

Related Entries

Decoding convolutional codes – Inventing Communication Algorithms via Machine Learning
Read more Decoding convolutional codes – Inventing Communication Algorithms via Machine Learning
0 users, 1 mentions 2020/02/04 03:51
ASPLOS'20 - Session 13B - Optimus Prime: Accelerating Data Transformation in Servers - YouTube
Read more ASPLOS'20 - Session 13B - Optimus Prime: Accelerating Data Transformation in Servers - YouTube
0 users, 1 mentions 2021/10/24 04:37
Differentiable Self-Adaptive Learning Rate | OpenReview
Read more Differentiable Self-Adaptive Learning Rate | OpenReview
0 users, 1 mentions 2021/11/11 06:09
[1902.04620] Extreme Tensoring for Low-Memory Preconditioning
Read more [1902.04620] Extreme Tensoring for Low-Memory Preconditioning
0 users, 1 mentions 2021/11/25 03:08
BayLearn 2021: Poster A-1: LocoProp: Enhancing BackProp via Local Loss Optimization - YouTube
Read more BayLearn 2021: Poster A-1: LocoProp: Enhancing BackProp via Local Loss Optimization - YouTube
0 users, 1 mentions 2021/12/07 04:37
[1804.09849] The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
Read more [1804.09849] The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
0 users, 1 mentions 2021/12/08 01:26

ML-Newsについて

ML-Newsは機械学習に関するニュースサイトです。機械学習に関する論文ブログライブラリコンペティション発表資料勉強会などの最新の情報にアクセスできます。

機械学習を応用した自然言語処理、画像認識、情報検索などの分野の情報や機械学習で必要になるデータ基盤やMLOpsの話題もカバーしています。
安定したサイト運営のためにGitHub sponsorを募集しています。

お知らせ

  • 2021/12/31: デザインを刷新しました
  • 2021/04/08: 日本語Kaggleのカテゴリを新設しました