TR2018-184

Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders


    •  Ozdenizci, O., Wang, Y., Koike-Akino, T., Erdogmus, D., "Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders", Tech. Rep. TR2018-184, Mitsubishi Electric Research Laboratories, Cambridge, MA, December 2018.
      BibTeX Download PDF
      • @techreport{MERL_TR2018-184,
      • author = {Ozdenizci, O. and Wang, Y. and Koike-Akino, T. and Erdogmus, D.},
      • title = {Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR2018-184},
      • month = dec,
      • year = 2018,
      • url = {http://www.merl.com/publications/TR2018-184/}
      • }
  • MERL Contacts:
  • Research Areas:

    Artificial Intelligence, Signal Processing


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.