AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Using noise to probe recurrent neural network structure and prune synapses

Eli Moore, Rishidev Chaudhuri

NeurIPS 2020 · Probabilistic and scientific modeling › Dynamical systems · approach: Synaptic plasticity learning rules · 1 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 noise-covariance-based sampling probabilities instead of weight-proportional probabilities for pruning (ablation)noise-prune on symmetric clustered networks · Diagonally-dominant clustered networksrelative eigenvalue change, quadratic form change, eigenvector alignmentImproved
Increase network sizenoise-prune · Diagonally-dominant clustered networksspectrum preservationImproved
Use noise covariance rather than weight-only sampling (ablation)noise-prune · Dynamical response to random and slow-eigenvector inputs, symmetric networkspreservation of network responseImproved
Apply rule to non-symmetric networks, beyond the theory (ablation)noise-prune · Non-symmetric clustered networks, random and eigenvector inputspreservation of network dynamicsImproved

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