Transfer learning of deep neural network representations for fMRI decoding.

Journal: Journal of neuroscience methods
Published Date: Dec 1, 2019

Abstract

BACKGROUND: Deep neural networks have revolutionised machine learning, with unparalleled performance in object classification. However, in brain imaging (e.g., fMRI), the direct application of Convolutional Neural Networks (CNN) to decoding subject states or perception from imaging data seems impractical given the scarcity of available data.

Authors

  • Michele Svanera
    Department of Information Engineering, University of Brescia, Italy; Institute of Neuroscience and Psychology, University of Glasgow, UK. Electronic address: Michele.Svanera@glasgow.ac.uk.
  • Mattia Savardi
    Information Engineering Dept., University of Brescia, Brescia, Italy.
  • Sergio Benini
    Department of Information Engineering, University of Brescia, Italy.
  • Alberto Signoroni
    Information Engineering Dept., University of Brescia, Brescia, Italy. Electronic address: alberto.signoroni@unibs.it.
  • Gal Raz
    Sagol Brain Institute, Wohl Institute for Advanced Imaging, Tel-Aviv Sourasky Medical Center, Tel-Aviv, Israel; Sagol School of Neuroscience, Tel-Aviv University, Tel-Aviv, Israel; The Steve Tisch School of Film and Television, Tel-Aviv University, Tel-Aviv, Israel.
  • Talma Hendler
    Functional Brain Center.
  • Lars Muckli
    Institute of Neuroscience and Psychology, University of Glasgow, UK.
  • Rainer Goebel
  • Giancarlo Valente
    Department of Cognitive Neuroscience, Maastricht University, Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals