AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Input-Output Equivalence of Unitary and Contractive RNNs

Melikasadat Emami, Mojtaba Sahraee Ardakan, Sundeep Rangan, Alyson K. Fletcher

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Efficient recurrent architectures · 3 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 a URNN with up to twice the hidden statesContractive ReLU RNN · Bounded input sequencesinput-output equivalenceImproved
Increase the URNN hidden-state count to twice the RNN countRNN and URNN · Synthetic slowly-varying dynamical systemstest errorNo clear effect
Impose a contractivity constraintRNN · Pixel-Permuted MNISTaccuracyImproved
Impose a unitary constraintRNN · Pixel-Permuted MNISTaccuracyImproved
Replace ReLU with sigmoid activationContractive RNN · Neighborhood of an input where the URNN is controllable and observableexact input-output equivalenceHurt
Limit the equivalent URNN to fewer than twice the RNN's hidden statesContractive ReLU RNN · Worst-case exact matchingminimum hidden-state count for equivalenceHurt

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