English

Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders

Machine Learning 2018-12-18 v1 Human-Computer Interaction Signal Processing

Abstract

We introduce adversarial neural networks for representation learning as a novel approach to transfer learning in brain-computer interfaces (BCIs). The proposed approach aims to learn subject-invariant representations by simultaneously training a conditional variational autoencoder (cVAE) and an adversarial network. We use shallow convolutional architectures to realize the cVAE, and the learned encoder is transferred to extract subject-invariant features from unseen BCI users' data for decoding. We demonstrate a proof-of-concept of our approach based on analyses of electroencephalographic (EEG) data recorded during a motor imagery BCI experiment.

Keywords

Cite

@article{arxiv.1812.06857,
  title  = {Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders},
  author = {Ozan Ozdenizci and Ye Wang and Toshiaki Koike-Akino and Deniz Erdogmus},
  journal= {arXiv preprint arXiv:1812.06857},
  year   = {2018}
}

Comments

9th International IEEE EMBS Conference on Neural Engineering (NER'19)

R2 v1 2026-06-23T06:44:45.376Z