AI Paper Atlas

Research map / Optimization / Optimizers

MomentumRNN: Integrating Momentum into Recurrent Neural Networks

Tan Nguyen, Richard Baraniuk, Andrea Bertozzi, Stanley Osher, Bao Wang

NeurIPS 2020 · Optimization › Optimizers · approach: Adam convergence and adaptive learning rates · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add a momentum state to LSTMLSTM · PMNISTtest accuracy (%): 92.29 -> 94.72Improved
Add a momentum state to LSTMLSTM · TIMIT testMSE: 9.37 -> 5.87Improved
Add a momentum state to LSTMLSTM · Copying, sequence length 2Ktraining loss: 0.01 -> 0.009Improved
Add a momentum state to LSTMLSTM · Adding, sequence length 750training loss: 0.162 -> 0.162No clear effect
Add a momentum state to LSTMLSTM · PTB word-level testperplexity: 59.71 \pm 0.99 -> 58.62 \pm 0.22Improved
Add a momentum state to DTRIVDTRIV · PMNISTtest accuracy (%): 96.62 \pm 0.12 -> 96.89 \pm 0.08Improved
Add a momentum state to DTRIVDTRIV · TIMIT testMSE: 1.87 \pm 0.17 -> 1.17 \pm 0.05Improved
Replace standard momentum updates with Adam-style recurrent updatesMomentumLSTM · PMNISTtest accuracy (%): 94.72 \pm 0.16 -> 95.38 \pm 0.19Improved
Use AdamLSTM or RMSPropLSTM instead of MomentumLSTMLSTM · TIMIT testMSE: 5.87 \pm 0.15 -> 8.69 \pm 0.14 (AdamLSTM); 9.17 \pm 0.33 (RMSPropLSTM)Hurt
Use scheduled-restart momentum instead of constant momentumMomentumLSTM · TIMIT testMSE: 5.87 \pm 0.15 -> 5.83 \pm 0.10Improved
Use Adam-style recurrent updates instead of standard momentumMomentumLSTM · Copying and adding taskstraining lossImproved
Use AdamLSTM or RMSPropLSTM instead of LSTMLSTM · PTB word-level testperplexity: 59.71 \pm 0.99 -> 61.11 \pm 0.31 (AdamLSTM); 64.53 \pm 0.20 (RMSPropLSTM)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy