AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

A mechanistic multi-area recurrent network model of decision-making

Michael Kleinman, Chandramouli Chandrasekaran, Jonathan Kao

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired recurrent architectures · 5 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 3 areas instead of a single-area RNN (ablation)mechanistic multi-area RNN · Checkerboard TaskPMd resemblance of last areaImproved
add Dale's law with anatomically-informed feedforward inhibition (ablation)mechanistic multi-area RNN · Checkerboard Taskcolor decode accuracy in Area 3Improved
reduce feedforward E-to-I connections to 2% or less (ablation)mechanistic multi-area RNN · Checkerboard Taskcolor decode accuracy in Area 3: 2%Improved
lower feedforward connections to 1% without Dale's law (ablation)mechanistic multi-area RNN · Checkerboard Taskcolor decode accuracy in Area 3: 1%No clear effect
vary feedforward E-E and feedback connection percentages (ablation)mechanistic multi-area RNN · Checkerboard Taskcolor decode accuracyNo clear effect
use at least 3 areas (ablation)mechanistic multi-area RNN · Checkerboard TaskPMd-like last areaImproved
vary ML hyperparameters (units, learning rate) (ablation)mechanistic multi-area RNN · Checkerboard Taskminimal color representationNo clear effect
train without Dale's law or with 2 areas (ablation)mechanistic multi-area RNN · Checkerboard Taskdirection axis alignment with top singular vectorsHurt
double 10% of inhibitory weights to the right poolmechanistic multi-area RNN · Area 3 psychometric curvechoice bias: 10%Improved
later areas (Area 1 to Area 3)mechanistic multi-area RNN · Checkerboard Taskcolor decode accuracy: 0.93, 0.76, 0.51Improved

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