AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation

Junfeng Zuo, Xiao Liu, Ying Nian Wu, Si Wu, Wenhao Zhang

NeurIPS 2023 · Probabilistic and scientific modeling › Dynamical systems · approach: Synaptic plasticity learning rules · 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
apply a time-invariant control input with gain alpha to the continuous attractor networkRecurrent CAN circuit · Network simulationneural sequence time scaleImproved
use a negative control input gain (alpha < 0)Recurrent CAN circuit · Network simulationtime-reversed neural sequenceImproved
change input gain across sequences of the same polarity vs different polaritiesSingle neuron responses · Network simulationoverlap of single-neuron temporal responses after rescalingMixed
add multiplicative (Poisson-like) noise to the recurrent circuitRecurrent CAN circuit · Network simulationstd of sequence duration vs mean (Weber's law)Improved
increase control input gainRecurrent CAN circuit with multiplicative noise · Network simulationmean sequence durationImproved
vary control input gain at test time after training feedforward circuit at one temporal scaleRecurrent circuit plus 3-layer perceptron · Handwritten digit 6 sequencegeneralization across temporal scalesImproved
use negative gain for the handwritten sequence generatorRecurrent circuit plus 3-layer perceptron · Handwritten digit 6 sequencereversed-order sequence generationImproved
switch to a different digit pattern without retraining the feedforward circuitDisentangled circuit · Handwritten digitspattern generationHurt

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