Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders
This addresses the challenge of adapting BCIs to new users more efficiently, though it appears incremental as it builds on existing transfer learning and adversarial methods.
The paper tackles the problem of subject variability in brain-computer interfaces by introducing adversarial neural networks with conditional variational autoencoders to learn subject-invariant representations, demonstrating a proof-of-concept on EEG data from a motor imagery experiment.
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.