mlsanityData to 14 Oct 2026

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

arXiv 2301.05869 ↗First posted 14 Jan 2023cs.LG stat.ME stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

It is desirable for statistical models to detect signals of interest independently of their position. If the data is generated by some smooth process, this additional structure should be taken into account. We introduce a new class of neural networks that are shift invariant and preserve smoothness of the data: functional neural networks (FNNs). For this, we use methods from functional data analysis (FDA) to extend multi-layer perceptrons and convolutional neural networks to functional data. We propose different model architectures, show that the models outperform a benchmark model from FDA in terms of accuracy and successfully use FNNs to classify electroencephalography (EEG) data.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 11 of its 47 references that are in the map. First posted on arXiv 14 Jan 2023.

Builds on

11 of 47 references.

References · 11

  1. 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
  2. 2018Deep learning for time series classification: a reviewcited by 576
  3. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 360
  4. 2019Deep learning-based electroencephalography analysis: a systematic reviewcited by 156
  5. 2019A review of feature extraction and performance evaluation in epileptic seizure detection using EEGcited by 29
  6. 2018Towards a universal neural network encoder for time seriescited by 28
  7. 2021Modern Non-Linear Function-on-Function Regressioncited by 11
  8. 2020A Non-linear Function-on-Function Model for Regression with Time Series Datacited by 8
  9. 2019Remaining Useful Life Estimation Using Functional Data Analysiscited by 7
  10. 2015The mRMR variable selection method: a comparative study for functional datacited by 5
  11. 2020A Portmanteau-type test for detecting serial correlation in locally stationary functional time seriescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 2.

9 papers.

  1. 2025Shape-Informed Clustering of Multi-Dimensional Functional Data via Deep Functional Autoencoderscited by 4
  2. 2024GT-PCA: Effective and Interpretable Dimensionality Reduction with General Transform-Invariant Principal Component Analysiscited by 2
  3. 2024EEG-MACS: Manifold Attention and Confidence Stratification for EEG-based Cross-Center Brain Disease Diagnosis under Unreliable Annotationscited by 2
  4. 2024Functional relevance based on the continuous Shapley valuecited by 1
  5. 2025Consumer-grade EEG-based Eye Trackingcited by 1
  6. 2025EEG-EyeTrack: A Benchmark for Time Series and Functional Data Analysis with Open Challenges and Baselinescited by 1
  7. 2025A Composable Channel-Adaptive Architecture for Seizure Classificationcited by 0
  8. 2026Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignmentcited by 0
  9. 2026Geometric Feature Learning for Functional Data Valued on the Symmetric Positive Definite Manifoldcited by 0