Dr Michael Burkhart

Research Associate

Contact information

University of Cambridge
Craik–Marshall Building
Cambridge
CB2 3EB
United Kingdom

Biography

Michael earned his Ph.D. in 2019 from Brown University's Division of Applied Mathematics. He and his advisor, Matthew Harrison, collaborated with the BrainGate clinical trial that develops intracortical brain–computer interfaces to enable persons with quadriplegia to communicate and interact with their environments using mental imagery alone. Together with Leigh Hochberg and David Brandman, they derived and implemented a novel Bayesian filtering framework to predict a participant’s latent intention given all currently available measurements from chronically implanted microarrays. After completing his doctorate, Michael spent three years working as a machine learning scientist at Adobe in California before joining the University of Cambridge as a research associate.

Research interests

sequential Bayesian inference, semi-supervised learning, causality, neurodegenerative disease

Keywords

Bayesian methods, Machine learning

Publications

M. Burkhart & G. Ruiz. Neuroevolutionary representations for learning heterogeneous treatment effects. Journal of Computational Science 71 (2023)

M. Burkhart. Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions. Optimization Letters 17 (2023)

M. Burkhart & K. Shan. Deep Low-Density Separation for Semi-supervised Classification. Computational Science – ICCS 2020

M. Burkhart, D. Brandman, B. Franco, L. Hochberg, & M. Harrison. The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Nongaussian Observation Models. Neural Computation 32 (2020)

M. Burkhart. “A Discriminative Approach to Bayesian Filtering with Applications to Human Neural Decoding.” Ph.D. Dissertation, Brown University (2019)

D. Brandman, M. Burkhart, J. Kelemen, B. Franco, M. Harrison, & L. Hochberg. Robust Closed-Loop Control of a Cursor in a Person with Tetraplegia using Gaussian Process Regression. Neural Computation 30 (2018)

About us

The Cambridge Centre for Data-Driven Discovery (C2D3) brings together researchers and expertise from across the academic departments and industry to drive research into the analysis, understanding and use of data science and AI. C2D3 is an Interdisciplinary Research Centre at the University of Cambridge.

  • Supports and connects the growing data science and AI research community 
  • Builds research capacity in data science and AI to tackle complex issues 
  • Drives new research challenges through collaborative research projects 
  • Promotes and provides opportunities for knowledge transfer 
  • Identifies and provides training courses for students, academics, industry and the third sector 
  • Serves as a gateway for external organisations 

Join us