Mike Hughes - Machine Learning Research

Welcome! My research spans statistical machine learning and its applications in healthcare and the sciences.

I am an Assistant Professor in the Dept. of Computer Science at Tufts University. Previously, I was a postdoctoral fellow in computer science at Harvard SEAS, advised by Prof. Finale Doshi-Velez. I did my Ph.D. in CS at Brown University in May 2016, advised by Prof. Erik Sudderth (now at UC-Irvine).

Research Highlights

Recently, my work is motivated by two exciting clinical applications:

  • antidepressant drug recommendations for patients with major depression
  • forecasting need for interventions in the Intensive Care Unit (ICU)

These applications have inspired new contributions to machine learning:

  • Semi-supervised learning: Our paper at AISTATS 2018 fits latent variable models so that they provide accurate predictions (e.g. drug recommendations) and interpretable generative models, even when labeled examples are rare.

  • Explainable AI: Our paper at AAAI 2018 introduces "Tree Regularization", a method to optimize deep neural networks so learned class boundaries are similar to decision trees (the trees can then be inspected by domain experts).