AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Functional Neural Networks: Shift invariant models for functional data with applications to EEG classification

Florian Heinrichs, Mavin Heim, Corinna Weber

ICML 2023 · Architectures and efficiency › CNN design · approach: Biologically inspired CNN explanation · 0 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
replace scalar layers with functional convolutional and dense layers (FNN)simulated datasets I and II · simulated data, N=1000 to 5000accuracyImproved
use shift-invariant functional convolutions instead of MLP-style layerssliding-window simulated dataset II · simulated dataset IIaccuracy: MLP 79.0%-90.7% vs FNN 99.6%-99.9%Improved
functional networks (FNN) vs EEGNet on phoneme datasetphoneme periodogram classification · phonemeaccuracy: 91.53 vs 87.83Improved
FNN vs EEGNet under the classic (cue-aligned) EEG approachBCI Competition IV 2A classic 4-class · EEG classic approachaccuracy: EEGNet 72.13 vs best FNN 69.08Hurt
functional CNN (FNN(40)) vs EEGNet under sliding windowsBCI Competition IV 2A sliding-window 7-class · EEG sliding windowsaccuracy: 56.29 vs 51.81 (+4.48)Improved
fully functional (per-time-point) predictions vs scalar window classification (ablation)Func2Func models on sliding-window EEG · EEG sliding windowsaccuracy: Func2Func(2) 51.52 and Func2Func(3) 47.33 vs scalar FNN(40) 56.29Hurt
reduce filters from 40+20 to 5+10 in sliding-window FNN (ablation)FNN for sliding-window EEG · EEG sliding windowsaccuracy: 52.12 vs 51.70 for 40+20No clear effect
single functional dense layer (F-MLP) instead of functional convolutions on classic EEG (ablation)classic EEG approach · EEG classic approachaccuracy: F-MLP(20) 66.31 vs FNN(20) 67.23No clear effect
increase filters from 20 to 40 in the single-conv-layer sliding-window FNN (FNN(20) to FNN(40)) (ablation)FNN sliding-window EEG · EEG sliding windowsaccuracy: 55.43 vs 56.29Improved

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