Functional Neural Networks: Shift Invariant Models for Functional Data with Applications to EEG Classification
Abstract
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.
Cite
Text
Heinrichs et al. "Functional Neural Networks: Shift Invariant Models for Functional Data with Applications to EEG Classification." International Conference on Machine Learning, 2023.Markdown
[Heinrichs et al. "Functional Neural Networks: Shift Invariant Models for Functional Data with Applications to EEG Classification." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/heinrichs2023icml-functional/)BibTeX
@inproceedings{heinrichs2023icml-functional,
title = {{Functional Neural Networks: Shift Invariant Models for Functional Data with Applications to EEG Classification}},
author = {Heinrichs, Florian and Heim, Mavin and Weber, Corinna},
booktitle = {International Conference on Machine Learning},
year = {2023},
pages = {12866-12881},
volume = {202},
url = {https://mlanthology.org/icml/2023/heinrichs2023icml-functional/}
}