- Developing Neural Topographic Factor Analysis (NTFA), Northeastern University
- Incorporated neural networks and matrix factorization methods to model individual and content variation in fMRI neural activities in Python and PyTorch
- Reduced dimensionality of fMRI time series data with interpretable low-dimensional embeddings
- Added an individual by content interaction embedding to account for both between and within individual variability
- Incorporated clustering methods to determine brain states in the embedding space
- Collaborated with an interdisciplinary team including machine learning researchers and neuroscientists
Khan, Z., Wang, Y., Sennesh, E., Dy J., Ostadabbas, S., van de Meent, J.W., Hutchinson, J.B., & Satpute, A.B. A computational neural model for mapping degenerate neural architectures Neuroinformatics (2022) * equal author contributions
Sennesh, E., Khan, Z., Wang, Y., Hutchinson, J.B., Satpute, A.B, Dy, J., & van de Meent, J. W. (2020). Neural topographic factor analysis for fMRI data. Advances in Neural Information Processing Systems (NeurIPS), 33, 12046-12056.
- Identifying Neural and Physiological Patterns of Fear, Northeastern University
- Developed situation- and individual-dependent models of subjective experiences of fear
- Designed, collected, preprocessed and analyzed fMRI data
- Collected, preprocessed, and analyzed physiological data (ECG, ICG, Respiration, EDA)
- Built neural predictors of fear using PCA, LASSO regression, and multivariate analysis
Wang. Y., Kragel, P.A., Satpute, A.B. (under review, bioRxiv) Neural predictors of subjective fear depend on the situation.
- Modeling social action conceptualization and prediction, Northeastern University
- Designed experiment, created the video stimuli, collected fMRI and online data
- Applied Reinforcement Learning models and Hierarchical Gaussian Filters to data
- Motivational influences on visual perception : a computational account
- 2016 - 2017 @ Stanford University
- Examined what people want to see influences what they report seeing
- Analyzed behavioral and mouse-tracking data using Drift Diffusion Model
Leong, Y.C., Hughes, B., Wang, Y., & Zaki, J. (2019). Neurocomputational mechanisms underlying motivated seeing. Nature Human Behavior, https://doi.org/10.1038/s41562-019- 0637-z
