AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Neural system identification for large populations separating “what” and “where”

David Klindt, Alexander S Ecker, Thomas Euler, Matthias Bethge

NeurIPS 2017 · Architectures and efficiency › CNN design · approach: Biologically inspired CNN explanation · 48 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 a sparse factorized readout that jointly learns receptive-field locations and feature weightsCNN neural system identification · Mouse V1 scans 1–3correlation: 0.47 -> 0.50Improved
Replace the factorized readout with a fully connected readout (ablation)CNN neural system identification · Mouse V1 averagecorrelation: 0.50 -> 0.43Hurt
Fix receptive-field masks using spike-triggered averages instead of optimizing them jointly (ablation)CNN neural system identification · Mouse V1 averagecorrelation: 0.50 -> 0.42Hurt
Use an LNP model instead of a shared convolutional feature model with factorized readoutMouse V1 neural response prediction · Mouse V1 averagecorrelation: 0.36 -> 0.50Hurt
Use a shared feature space across neurons rather than fitting each neuron independentlyCNN system identification · Homogeneous linear populationFEV: same level of performance with less than a quarter of the dataImproved
Estimate receptive-field locations in advance with spike-triggered averages rather than learning them jointly (ablation)CNN system identification · Synthetic nonlinear VGG feature populationFEVHurt
Use a fully connected readout instead of the factorized readout (ablation)CNN system identification · Synthetic nonlinear VGG feature populationFEVHurt
Increase the diversity of neuron types in the population (ablation)CNN with factorized readout · Synthetic VGG populationFEVNo clear effect
Increase the diversity of neuron types with a fully connected readout (ablation)CNN with fully connected readout · Synthetic VGG populationFEVHurt
Use L1 sparsity on feature weights to encourage each neuron to select a feature channel (ablation)CNN with factorized readout · Two-type linear populationcell-type interpretabilityImproved
Use the ground-truth convolution kernel and optimize only location masks (ablation)CNN system identification · Homogeneous linear populationFEVNo clear effect

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