Skip to main content

Transforming the understanding
and treatment of mental illnesses.

Celebrating 75 Years! Learn More >>

Photo of Francisco Pereira, Ph.D.

Francisco Pereira, Ph.D.

Machine Learning Team

Research Topics

The mission of the Machine Learning Team (MLT) is to support researchers in the NIMH intramural research program (IRP) who want to address research problems in clinical and cognitive neuroscience using machine learning approaches.

We do this by consulting with individual researchers and guiding them in the use of the appropriate tools and methods, or by taking on the analysis process ourselves, if this is more expedient. In parallel, we develop new methods and analysis approaches, motivated by the needs of researchers or by the practical possibilities arising from advances in the field.


Francisco Pereira leads the Machine Learning Team within the Section on Functional Imaging Methods at the National Institute of Mental Health, in Bethesda, Maryland. Prior to that, he was a staff scientist at Siemens Healthcare, where he managed the Computational Neuroscience program. He did his postdoc at the Princeton Neuroscience Institute, working with Matt Botvinick and Ken Norman, as well as anyone stopping by his office with an interesting question and chocolate. He received a Ph.D. in Computer Science and Neural Basis of Cognition from Carnegie Mellon University, where he worked with Tom Mitchell and Marcel Just, and an undergraduate degree in Computer Science from Universidade do Porto. He promises not to talk about himself in the third person if you come to his office.

Selected Publications

Toward a universal decoder of linguistic meaning from brain activation . Pereira F, Lou B, Pritchett B, Ritter S, Gershman SJ, Kanwisher N, Botvinick M, Fedorenko E. Nat Commun. 2018 Mar 6;9(1):963. doi: 10.1038/s41467-018-03068-4 PMID: 29511192.

A comparative evaluation of off-the-shelf distributed semantic representations for modelling behavioural data . Pereira F, Gershman S, Ritter S, Botvinick M.. Cogn Neuropsychol. 2016 May-Jun;33(3-4):175-90. doi: 10.1080/02643294.2016.1176907 PMID: 27686110.

Using Wikipedia to learn semantic feature representations of concrete concepts in neuroimaging experiments . Pereira F, Botvinick M, Detre G. Artif Intell. 2013 Jan 1;194:240-252. Epub 2012 Jul 10 PMID: 23243317.

Generating text from functional brain images . Pereira F, Detre G, Botvinick M. Front Hum Neurosci. 2011 Aug 23;5:72. doi: 10.3389/fnhum.2011.00072. eCollection 2011 PMID: 21927602.

Information mapping with pattern classifiers: a comparative study . Pereira F, Botvinick M. Neuroimage. 2011 May 15;56(2):476-96. doi: 10.1016/j.neuroimage.2010.05.026. Epub 2010 May 17 PMID: 20488249.

Reproducibility distinguishes conscious from nonconscious neural representations . Schurger A, Pereira F, Treisman A, Cohen JD. Science. 2010 Jan 1;327(5961):97-9. doi: 10.1126/science.1180029. Epub 2009 Nov 12 PMID: 19965385.

Machine learning classifiers and fMRI: a tutorial overview . Pereira F, Mitchell T, Botvinick M. Neuroimage. 2009 Mar;45(1 Suppl):S199-209. doi: 10.1016/j.neuroimage.2008.11.007. Epub 2008 Nov 21. Review PMID: 19070668.

Magnuson Clinical Center, Room 3D41

Phone: +1 301 827 2632