Avatar

Pascal Sturmfels

PhD Student in Machine Learning

University of Washington

Biography

I am currently a PhD student at the University of Washington, advised by Su In Lee. I am interested in developing methods to make machine learning models more interpretable, and applying such methods to understand biological and health data.

Interests

  • Machine Learning
  • Explainable AI

Education

  • PhD in Artificial Intelligence, Current

    University of Washington

  • B.E. in Computer Science, 2017

    University of Michigan

Recent Publications

Explaining Explanations: Axiomatic Feature Interactions for Deep Networks

PDF

Visualizing the Impact of Feature Attribution Baselines

PDF

Automated brain masking of fetal functional MRI

PDF

Learning explainable models using attribution priors

PDF
See all publications

Projects

Path Explanations

A GitHub package to explain not only which features are most important to a neural network prediction, but also how those features interact with each other.

Attribution Priors

A GitHub package to regularize a neural network’s feature attributions during training in order to encode human-level prior knowledge into the training process.