`

Timezone: »

 
Poster
Neural Topographic Factor Analysis for fMRI Data
Eli Sennesh · Zulqarnain Khan · Yiyu Wang · J Benjamin Hutchinson · Ajay Satpute · Jennifer Dy · Jan-Willem van de Meent

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1335

Neuroimaging studies produce gigabytes of spatio-temporal data for a small number of participants and stimuli. Recent work increasingly suggests that the common practice of averaging across participants and stimuli leaves out systematic and meaningful information. We propose Neural Topographic Factor Analysis (NTFA), a probabilistic factor analysis model that infers embeddings for participants and stimuli. These embeddings allow us to reason about differences between participants and stimuli as signal rather than noise. We evaluate NTFA on data from an in-house pilot experiment, as well as two publicly available datasets. We demonstrate that inferring representations for participants and stimuli improves predictive generalization to unseen data when compared to previous topographic methods. We also demonstrate that the inferred latent factor representations are useful for downstream tasks such as multivoxel pattern analysis and functional connectivity.

Author Information

Eli Sennesh (Northeastern University)

I work in the Probabilistic Modeling Lab at Northeastern University’s CCIS, as well as the Interdisciplinary Affective Science Laboratory. We use the tools of machine learning, statistics, and computation to study the deep questions at the heart of neuroscience, cognition, and agency. We’re making the world a better place through probabilistic programming!

Zulqarnain Khan (Northeastern University)

PhD Candidate at Machine Learning Lab at Northeastern University with Prof. Jennifer Dy. Interests include Clustering, Graphical Models, Factor Analysis, Variational Inference.

Yiyu Wang (Northeastern University)
J Benjamin Hutchinson (University of Oregon)
Ajay Satpute (Northeastern)
Jennifer Dy (Northeastern University)
Jan-Willem van de Meent (Northeastern University)

More from the Same Authors