Published in

Frontiers Media, Frontiers in Neuroscience, (8), 2014

DOI: 10.3389/fnins.2014.00229

Links

Tools

Export citation

Search in Google Scholar

Deep learning for neuroimaging: A validation study

Journal article published in 2014 by Sergey M. Plis, Devon R. Hjelm, Ruslan Salakhutdinov, Elena A. Allen, Henry J. Bockholt, Jeffrey D. Long, Hans J. Johnson, Jane S. Paulsen, Jessica A. Turner ORCID, Vince D. Calhoun
This paper is made freely available by the publisher.
This paper is made freely available by the publisher.

Full text: Download

Green circle
Preprint: archiving allowed
Upload
Green circle
Postprint: archiving allowed
Upload
Green circle
Published version: archiving allowed
Upload
Policy details
Data provided by SHERPA/RoMEO

Abstract

Deep learning methods have recently made notable advances in the tasks of classification and representation learning. These tasks are important for brain imaging and neuroscience discovery, making the methods attractive for porting to a neuroimager's toolbox. Success of these methods is, in part, explained by the flexibility of deep learning models. However, this flexibility makes the process of porting to new areas a difficult parameter optimization problem. In this work we demonstrate our results (and feasible parameter ranges) in application of deep learning methods to structural and functional brain imaging data. These methods include deep belief networks and their building block the restricted Boltzmann machine. We also describe a novel constraint-based approach to visualizing high dimensional data. We use it to analyze the effect of parameter choices on data transformations. Our results show that deep learning methods are able to learn physiologically important representations and detect latent relations in neuroimaging data.