Michael Burkhart
Sr. Data Scientist
Chicago, Illinois, United States
Summary
👤
Senior🎓
Top SchoolMichael Burkhart is a senior data scientist with nine years of experience applying advanced machine learning to healthcare and consumer problems, currently developing ML solutions in the Beaulieu-Jones Lab at the University of Chicago. He holds a PhD in Applied Mathematics from Brown and has blended academic rigor with industry impact through roles at Cambridge and Adobe, where he built causal and personalized models at scale. His research has spanned neural decoding and brain–computer interfaces, graph neural networks for predicting brain age, and automating covariate shift detection—demonstrating a knack for translating statistical theory into robust, production-ready pipelines. Comfortable across PyTorch Geometric, PySpark, LightGBM and causal forests, he pairs probabilistic modeling with practical data engineering to tackle noisy, longitudinal biomedical datasets. Based in Chicago, Michael is equally at home mentoring interns on representation learning as he is prototyping novel Bayesian and graph-based approaches for early disease diagnosis.
9 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy (PhD) Applied Mathematics, Doctor of Philosophy (PhD) Applied Mathematics at Brown UniversityB.Sc. Statistics Mathematics and Economics, B.Sc. Statistics Mathematics and Economics at Purdue UniversityM.Sc. Mathematics, M.Sc. Mathematics at Rutgers University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (50)
algorithms10
scipy10
python10
scientific-computing10
interpolation9
convolution9
numba8
finite-element-analysis8
numerics8
root-finding8
mpi8
anonymous8
numpy8
signature8
lapack8
Programming languages (6)
Github contributions (5)
burkh4rt/Filtered-Stochastic-Newton
May 2021 - May 2022
We apply sequential Bayesian inference with a discriminatively specified observation model to the subsampled gradients and Hessians used by the stochastic Newton method for online optimization.
Contributions:2 releases, 5 commits, 2 PRs in 1 year
observationgradientsbayesian-inferencemomentum-in-optimizationstochastic-newton-method
burkh4rt/DKF-implementations
May 2020 - Feb 2022
This repository contains code implementations for the Discriminative Kalman Filter.
Contributions:2 releases, 17 commits, 2 PRs in 1 year 9 months
implementationspythonbrain-computer-interfacecluster-computingkalman
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.