AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Low Tensor Rank Learning of Neural Dynamics

Arthur Pellegrino, N Alex Cayco Gajic, Angus Chadwick

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired recurrent architectures · 2 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 ltrRNN with 5 components instead of the full tensor RNN (ablation)ltrRNN · macaque motor learning dataheld-out unexplained varianceNo clear effect
allow weights to vary over trials (full tensor RNN) versus static RNN (ablation)RNN · macaque motor learning datavariance explained: ~5% differenceImproved
ltrRNN instead of truncated SVD and PARAFAC at low rankslow-rank models · macaque motor learning dataheld-out unexplained varianceImproved
double neurons from 200 to 400 (370 trials)ltrRNN · training timetraining time: 12min -> 22minHurt
double trials from 370 to 740 (200 neurons)ltrRNN · training timetraining time: 12min -> 16minHurt

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