AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems

Ingmar Kanitscheider, Ila Fiete

NeurIPS 2017 · Probabilistic and scientific modeling › Dynamical systems · approach: Recurrent circuit models of inference · 17 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
train LSTM on generalized task (novel environments) and retrain only readout for classification (ablation)Generalized LSTM network · 100 familiar environments classificationaccuracy (%): 1% (chance) -> close to 80%Improved
use recurrent LSTM network instead of path integration onlynavigation localization · Localization in familiar environmentmean abs errorImproved
use LSTM network instead of single hypothesis filternavigation localization · Localization in familiar environmentmean abs errorImproved

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