AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Cognitive Model Discovery via Disentangled RNNs

NeurIPS 2023 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent models of neural activity · 27 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
increase GRU hidden units from 2-3 to 14 (ablation)GRU on rat bandit data · Rat bandit datasetnormalized likelihood diff (pct points): 0.34 -> 0.50Helped
increase GRU hidden units beyond 2 (ablation)GRU on synthetic Q-Learning / Actor-Critic data · Synthetic bandit datasetsnormalized likelihood diff (pct points): 0.002 (Q-Learning), 0.02 (Actor-Critic)No clear effect
use very high beta (stronger bottleneck penalty) (ablation)DisRNN · Synthetic datasetscross-validated fitHurt
use medium beta (ablation)DisRNN · Synthetic datasetsrecovered model structureHelped
use very low beta (ablation)DisRNN · Synthetic datasetsmodel simplicity vs fitMixed
replace DisRNN with two-unit GRU (ablation)disentangled recovery of latent dynamics · Actor-Critic and Bounded Accumulator synthetic datarecovery of true update rulesHurt

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