Format

Send to

Choose Destination
Neural Comput. 2010 Dec;22(12):3127-42. doi: 10.1162/NECO_a_00047. Epub 2010 Sep 21.

Neural decoding with hierarchical generative models.

Author information

1
Radboud University Nijmegen, Institute for Computing and Information Sciences, 6525 AJ Nijmegen, the Netherlands. marcelge@cs.ru.nl

Abstract

Recent research has shown that reconstruction of perceived images based on hemodynamic response as measured with functional magnetic resonance imaging (fMRI) is starting to become feasible. In this letter, we explore reconstruction based on a learned hierarchy of features by employing a hierarchical generative model that consists of conditional restricted Boltzmann machines. In an unsupervised phase, we learn a hierarchy of features from data, and in a supervised phase, we learn how brain activity predicts the states of those features. Reconstruction is achieved by sampling from the model, conditioned on brain activity. We show that by using the hierarchical generative model, we can obtain good-quality reconstructions of visual images of handwritten digits presented during an fMRI scanning session.

PMID:
20858128
DOI:
10.1162/NECO_a_00047
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Atypon
Loading ...
Support Center