Interpretable Machine Learning for Affective Psychophysiology and Neuroscience

I am a Machine Learning researcher primarily interested in applying and developing machine learning models for interdisciplinary applications, especially in health sciences, and analyzing the theoretical underpinnings of explanation methods. 

Analyzing the Effects of Classifier Lipschitzness on Explainers

For a variety of explainers (e.g., SHAP, RISE, CXPlain), we provide lower bound guarantees on the astuteness of these explainers given the Lipschitzness of the prediction function. These theoretical results imply that locally smooth prediction functions lend themselves to locally robust explanations.

Neural Topographic Factor Analysis for fMRI Data

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.

A Computational Neural Model for Mapping Degenerate Neural Architectures

Degeneracy in biological systems refers to a many-to-one mapping between physical structures and their functional (including psychological) outcomes. Despite the ubiquity of the phenomenon, traditional analytical tools for modeling degeneracy in neuroscience are extremely limited. NTFA, with appropriate modifications can plug this gap.

Context-aware experience sampling reveals the scale of variation in affective experience

Emotion research typically searches for consistency and specificity in physiological activity across instances of an emotion category, such as anger or fear, yet studies to date have observed more variation than expected. In the present study, we adopt an alternative approach, searching inductively for structure within variation, both within and across participants.