AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Dis-inhibitory neuronal circuits can control the sign of synaptic plasticity

Julian Rossbroich, Friedemann Zenke

NeurIPS 2023 · Probabilistic and scientific modeling › Dynamical systems · approach: Synaptic plasticity learning rules

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 linear threshold rule instead of exact inverse rule (1 hidden layer) (ablation)dis-inhibitory control · MNISTtest accuracy: 97.7 -> 97.1Hurt
use linear threshold rule instead of exact inverse rule (3 hidden layers) (ablation)dis-inhibitory control · MNISTtest accuracy: 98.0 -> 96.5Hurt
use linear threshold rule instead of exact inverse rule (1 hidden layer) (ablation)dis-inhibitory control · Fashion-MNISTtest accuracy: 89.1 -> 87.6Hurt
use linear threshold rule instead of exact inverse rule (3 hidden layers) (ablation)dis-inhibitory control · Fashion-MNISTtest accuracy: 89.1 -> 86.8Hurt
replace input-dependent Jacobian feedback with average Jacobian feedback (3 hidden layers) (ablation)dis-inhibitory control, exact inverse · MNISTtest accuracy: 98.0 -> 97.0Hurt
replace input-dependent Jacobian feedback with average Jacobian feedback (3 hidden layers) (ablation)dis-inhibitory control, exact inverse · Fashion-MNISTtest accuracy: 89.1 -> 88.2Hurt
replace input-dependent Jacobian feedback with average Jacobian feedback (1 hidden layer) (ablation)dis-inhibitory control, exact inverse · MNISTtest accuracy: 97.7 -> 97.8No clear effect
replace input-dependent Jacobian feedback with average Jacobian feedback (3 hidden layers) (ablation)dis-inhibitory control, linear threshold · Fashion-MNISTtest accuracy: 86.8 -> 84.6Hurt
use exact-inverse dis-inhibitory control instead of backprop (1 hidden layer)MLP · MNISTtest accuracy: 98.1 -> 97.7No clear effect
use exact-inverse dis-inhibitory control instead of backprop (3 hidden layers)MLP · Fashion-MNISTtest accuracy: 89.4 -> 89.1Hurt
use linear threshold rule instead of exact inverse in student-teacher task (ablation)dis-inhibitory control · student-teacher sine taskMSE lossNo clear effect
increase depth from 1 to 3 hidden layers with linear threshold rule (ablation)dis-inhibitory control · MNISTtest accuracy: 97.1 -> 96.5Hurt

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