AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Cells in Multidimensional Recurrent Neural Networks

Gundram Leifert, Tobias Strauß, Tobias Grüning, Welf Wustlich, Roger Labahn

JMLR 2016 · Architectures and efficiency › RNNs and normalization · approach: Efficient recurrent architectures · 30 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
replace LSTM with LeakyLP in the lowest 2D layerMDRNN · IFN/ENIT validationmedian label error rate (%): 10,58% -> 8,93%Improved
replace LSTM with Leaky cell in the lowest 2D layerMDRNN · IFN/ENIT validationmedian label error rate (%): 10,58% -> 9,10%Improved
replace LSTM with Stable cell in the lowest 2D layerMDRNN · IFN/ENIT validationmedian label error rate (%): 10,58% -> 9,55%Improved
replace LSTM with LeakyLP in the lowest layer, spread across 10 initsMDRNN · IFN/ENIT validationmax label error rate (%): max 14,73% -> 9,40%Improved
also use LeakyLP in 2D layer 2 (LeakyLP/LeakyLP/LSTM) (ablation)MDRNN · IFN/ENIT validationmedian label error rate (%): 8,93% -> 8,91%No clear effect
also use LeakyLP in 2D layer 3 (all LeakyLP) (ablation)MDRNN · IFN/ENIT validationmedian label error rate (%): 8,91% -> 9,74%Hurt
raise learning rate from 1e-4 to 1e-3 for LSTM cells (ablation)LSTM MDRNN · IFN/ENIT validationmedian label error rate (%): 10,58% -> 11,44%; max 14,73% -> 30,20%Hurt
raise learning rate from 1e-4 to 5e-4 for LeakyLP cells (ablation)LeakyLP MDRNN · IFN/ENIT validationmedian label error rate (%): 9,74% -> 8,78%Improved
replace LSTM with LeakyLP in the lowest 2D layerMDRNN · Rimes validationmedian label error rate (%): 16,50% -> 15,30%Improved
replace LSTM with Stable cell in the lowest 2D layerMDRNN · Rimes validationmedian label error rate (%): 16,50% -> 15,11%Improved
replace LSTM with Leaky cell in the lowest 2D layerMDRNN · Rimes validationmedian label error rate (%): 16,50% -> 15,85%Improved
also use LeakyLP in 2D layer 2 (LeakyLP/LeakyLP/LSTM) (ablation)MDRNN · Rimes validationmedian label error rate (%): 15,30% -> 14,92%Improved

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