Workshop in Biostatistics

DATE: April 28, 2016
TIME: 1:30 - 3:00 pm
LOCATION: Medical School Office Building, Rm x303
TITLE: Brain reading using fMRI
SPEAKERS: Russell Polrack
Professor of Psychology, Stanford
and
Sanmi Koyejo
Research Associate, Department of Psychology, Stanford

Abstract:

There is great current interest in using brain imaging to decode psychological experiences from the brain.  We will outline a program of research that has developed methods for the decoding of mental processes from functional magnetic resonance imaging (fMRI) data.  We will focus particularly on multiclass and multilabel classification approaches, including theoretical results on consistent multilabel classification by reduction to standard binary classifiers. We will also discuss the development of encoding models that can provide a more interpretable basis for decoding.  

Suggested readings:

Poldrack, R.A. (2011). Inferring mental states from neuroimaging data: from reverse inference to large-scale decoding. Neuron, 72(5), 692-697. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3240863/

Koyejo, O. O., Natarajan, N., Ravikumar, P. K., & Dhillon, I. S. (2015). Consistent Multilabel Classification. In Advances in Neural Information Processing Systems (pp. 3303-3311). http://papers.nips.cc/paper/5883-consistent-multilabel-classification

Schwartz, Y., Thirion, B., & Varoquaux, G. (2013). Mapping cognitive ontologies to and from the brain. In Advances in Neural Information Processing Systems http://papers.nips.cc/paper/5168-mapping-paradigm-ontologies-to-and-from-the-brain.pdf