Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks

NeurIPSSpotlight2025

Authors: Ann Huang, Satpreet Harcharan Singh, Flavio Martinelli, Kanaka Rajan
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Task-trained recurrent neural networks (RNNs) are widely used in neuroscience and machine learning to model dynamical computations…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

control

← All NeurIPS 2025 Spotlight papers · Browse the whole archive