Center for Multimodal Neuroimaging

The mission of the Machine Learning Core is to support researchers in the NIMH intramural research program who want to address research problems in psychology, psychiatry, and neuroscience, using statistics and 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 are a machine learning research group and, as such, develop new methods and analysis approaches, motivated by the needs of researchers or by the practical possibilities arising from advances in the field.

contact: francisco.pereira@nih.gov

The Machine Learning Core supports researchers in the NIMH intramural research program who want to address research problems in clinical and cognitive neuroscience using machine learning approaches.

Google Scholar Profile

VICE toolbox for creating interpretable item embeddings from odd-one-out triplet task judgments
(the primary developer is Lukas Muttenthaler, please see VICE paper for the method we developed jointly)
R and python packages for fitting functional linear mixed effects models to fiber photometry data
(the primary developer is Gabriel Loewinger, please see fLMM paper for details)
Interpretability-Constrained Questionnaire Factorization, for generating interpretable factors and loadings from questionnaire data
(the primary developer is Ka Chun Lam, please see ICQF preprint for details)
R implementation of the one-step GEE algorithm for very large cluster sizes
(the primary developer is Gabriel Loewinger, please see fast GEE paper for details)

Harnessing Natural Language Processing for Automated Exposure Therapy Coding in Youth with OCD
Lossio-Ventura J.A., Frank S., Ringlein G., Bonson K., Olszko A., Knobel A., Pine D.S., Freeman J., Benito K., Jangraw D.C,
Fast Penalized Generalized Estimating Equations for Large Longitudinal Functional Datasets
Loewinger G., Levis A., Cui E., Pereira F.
Persistent representation of a prior schema in the orbitofrontal cortex facilitates learning of a conflicting schema
Maor I., Atwell J., Ascher I., Zhao Y., Takahashi Y.K., Hart E., Pereira F., Schoenbaum G.
Distinct prelimbic cortex ensembles encode response execution and inhibition
Madangopal R., Zhao Y., Heins C., Zhou U., Liang B., Barbera G., Lam K.C., Komer L.E., Weber S.J., Thompson D. J., Gera Y., Pham D.Q., Savell K.E., Warren B.L., Caprioli D., Venniro M., Bossert J.M., Ramsey L.A., Jedema H.P., Schoenbaum G., Lin D.T., Shaham Y., Pereira F., Hope B.T.
Nonparametric causal inference for optogenetics: sequential excursion effects for dynamic regimes
Loewinger G., Levis A., Pereira F.
Detecting Cry in Daylong Audio Recordings using Machine Learning: The Development and Evaluation of Binary Classifiers
Henry L.M., Lee K., Hansen E., Tandilashvili E., Rozsypal J., Erjo T., Raven J. G., Reynolds H. M., Curtis P., Haller S.,Pine D., Norton E., Wakschlag K.S., Pereira F., Brotman M.A.
The encoding of interoceptive-based predictions by the paraventricular nucleus of the thalamus D2+ neurons
Machen B., Miller S., Xin A., Lampert C., Assaf L., Tucker J., Pereira F., Loewinger G., Beas S.
In-Scanner Thoughts shape Resting-state Functional Connectivity: how participants “rest” matters
Gonzalez-Castillo J., Spurney M., Lam K.C., Gephart I. S., Pereira F., Handwerker D. A., Kam J. W. Y., Bandettini P.
Neural and behavioral reinstatement jointly reflect retrieval of narrative events
Nau M., Greene A., Tarder-Stoll H., Lossio-Ventura J.A., Pereira F., Chen J., Baldassano C., Baker C.I.
Interpretable factorization of clinical questionnaires to identify latent factors of psychopathology
Lam K.C., Mahony B.W., Raznahan A., Pereira F.

(click to jump to each section: Methods and Applications in Neuroscience, Psychiatry, and Cognitive Psychology/Neuroscience)

A Statistical Framework for Analysis of Trial-Level Temporal Dynamics in Fiber Photometry Experiments
Loewinger G., Cui E., Lovinger D., Pereira F.
in press at eLife, 2025
More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing
Shaier S., Pereira F., K von der Wense, LE Hunter, M Jones
in International Conference on Learning Representations, 2025
"Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion Effects"
Levis A., Loewinger G., Pereira
in Neural Information Processing Systems, 2024
A Comparison of ChatGPT and Fine-Tuned Open Pre-Trained Transformers (OPT) Against Widely Used Sentiment Analysis Tools: Sentiment Analysis of COVID-19 Survey Data
Lossio-Ventura J. A., Weger R., Lee A., Guinee E., Chung J. Y., Atlas L. Y., Linos E., Pereira F.
JMIR Mental Health Vol 11, 2024
"Improving the Interpretability of fMRI Decoding using Deep Neural Networks and Adversarial Robustness"
McClure P., Moraczewski D., Lam K. C., Thomas A., Pereira F.
Aperture Neuro, 2023
"Real-time variational method for learning neural trajectory and its dynamics"
Matthew Dowling, Yuan Zhao, Il Memming Park
in International Conference on Learning Representations, 2023
Linear time GPs for inferring latent trajectories from neural spike trains"
Matthew Dowling, Yuan Zhao, Il Memming Park
in International Conference on Machine Learning, 2023
"VICE: Variational Interpretable Concept Embeddings"
Muttenthaler L., Zheng C., McClure P., Vandermeulen R., Hebart M., Pereira F.
in Neural Information Processing Systems, 2022
Semantic Projection: Recovering Human Knowledge of Multiple, Distinct, Object Features from Word Embeddings
Grand G., Blank I., Pereira F., Fedorenko E.
Nature Human Behaviour, 2022
"Knowing What You Know in Brain Segmentation Using Bayesian Deep Neural Networks"
McClure, P., Rho, N., Lee, J., Kaczmarzyk, J., Zheng, C., Ghosh, S., Nielson, D., Thomas, A., Bandettini, P., Pereira, F.
Frontiers in Neuroinformatics, 2019
"Revealing interpretable object representations from human behavior"
Zheng, C., Pereira, F., Baker, C., Hebart, M.
International Conference on Learning Representations, 2019
"Validating the Representational Space of Deep Reinforcement Learning Models of Behavior with Neural Data"
Bruch S. N. , McClure P., Zhou J., Schoenbaum G., Pereira F.
bioRxiv preprint
A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes
McClure P. , Reimann G., Ramot M., Pereira F.
arXiv preprint
"Deep Neural Networks in Computational Neuroscience"
Kietzmann, T., McClure, P., Kriegeskorte, N.
Oxford Research Encyclopedia of Neuroscience, 2019
"Distributed Weight Consolidation: A Brain Segmentation Case Study"
McClure P., Zheng C., Kaczmarzyk J., Rogers-Lee J., Ghosh S., Nielson D., Bandettini P., Pereira F.
Neural Information Processing Systems, 2018
"Extrapolating Expected Accuracies for Large Multi-Class Problems"
Zheng, C., Achanta R., Benjamini. Y.
Journal of Machine Learning Research vol. 19. 2018.

"Manifold learning for fMRI time-varying functional connectivity"
Gonzalez-Castillo J., Fernandez I., Lam K., Handwerker D., Pereira F., Bandettini P.
Front Hum Neurosci. 2023; 17: 1134012
"The temporal representation of experience in subjective mood"
Keren H., Zheng C., Jangraw D. C., Chang K., Vitale A., Nielson D., Rutledge R. B., Pereira F., Stringaris A.
eLife 2021
"Mental representations of objects reflect the ways in which we interact with them"
Lam K. C., Pereira F., Vaziri-Pashkam M., Woodard K., McMahon E.
Proceedings of the Cognitive Science Society Conference, 2021 [selected for oral presentation]
"Revealing the multidimensional mental representations of natural objects underlying human similarity judgments"
Hebart, M., Zheng, C., Pereira, F., Baker, C.
Nature Human Behaviour, 2020
"Subtle predictive movements reveal actions regardless of social context"
McMahon, E.G., Zheng, C.Y., Pereira, F., Gonzalez, R., Ungerleider, L.G. and Vaziri-Pashkam, M.
Journal of vision 19 (7), 16-16, 2019
Imaging the spontaneous flow of thought: Distinct periods of cognition contribute to dynamic functional connectivity during rest
Gonzalez-Castillo J., Caballero-Gaudes C., Topolski N., Handwerker D., Pereira F. , Bandettini P.
Neuroimage 15; 202: 116129. 2019
"Toward a universal decoder of linguistic meaning from brain activation"
Pereira F., Lou B., Pritchett B., Ritter S., Gershman S., Kanwisher N., Botvinick M., Fedorenko E.
Nature Communications 9 (963), 2018