AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Multi-Zone Unit for Recurrent Neural Networks

Fandong Meng, Jinchao Zhang, Yang Liu, Jie Zhou

AAAI 2020 · Architectures and efficiency › RNNs and normalization · approach: Efficient recurrent architectures · 1 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
Use multi-zone recurrent transitions with self-attention, graph convolution, or capsulesRNNs · Penn Treebank testBPC: 1.190 -> 1.181Improved
Use multi-zone recurrent transitions with self-attention, graph convolution, or capsulesRNNs · text8 testBPC: 1.27 -> 1.249; 1.08Mixed
Use capsule-based multi-zone transitionsDeep transition GRU · SemEval 2014 Restaurant and Laptop, DS and HDSaccuracy: 78.25$\pm$0.51 -> 79.40$\pm$0.23; 56.17$\pm$0.72 -> 57.59$\pm$0.70; 71.01$\pm$0.73 -> 72.45$\pm$0.68; 47.03$\pm$1.15 -> Improved
Use 2 zones instead of 4 (ablation)satMZU+DT · Penn Treebank testBPC: 1.189 -> 1.191Hurt
Use 8 or 16 zones instead of 4 (ablation)satMZU+DT · Penn Treebank testBPC: 1.189 -> 1.200; 1.189 -> 1.208Hurt
Vary the zone count from 4 to 2, 8, or 16 (ablation)gcnMZU+DT · Penn Treebank testBPC: 1.183 -> 1.187; 1.183 -> 1.189; 1.183 -> 1.185Mixed
Vary the zone count from 4 to 2, 8, or 16 (ablation)capMZU+DT · Penn Treebank testBPC: 1.181 -> 1.186; 1.181 -> 1.181; 1.181 -> 1.186Mixed
Add a multi-zone gate function rather than a regular linear gate (ablation)satMZRNN · Penn Treebank test, shallow and deepBPC: 1.236 -> 1.214; 1.207 -> 1.189Improved
Add a multi-zone transformation function rather than a regular linear transformation (ablation)satMZRNN · Penn Treebank test, shallow and deepBPC: 1.247 -> 1.214; 1.208 -> 1.189Improved
Add a multi-zone gate function rather than a regular linear gate (ablation)gcnMZRNN · Penn Treebank test, shallow and deepBPC: 1.224 -> 1.196; 1.197 -> 1.183Improved
Add a multi-zone transformation function rather than a regular linear transformation (ablation)gcnMZRNN · Penn Treebank test, shallow and deepBPC: 1.225 -> 1.196; 1.191 -> 1.183Improved
Add a multi-zone gate function rather than a regular linear gate (ablation)capMZRNN · Penn Treebank test, shallow and deepBPC: 1.219 -> 1.192; 1.190 -> 1.181Improved

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