Hi! My name is Patrick Beukema. I am a research scientist in applied neuroscience and machine learning. Currently I am working on building brain machine interfaces using deep learning for end-to-end neural decoding at a startup in the D.C. area. I am also interested in improving the low replication rates in biomedical research.
Previously, I earned a Ph.D in neuroscience from the Center for Neuroscience at the University of Pittsburgh and the Center for the Neural Basis of Cognition at Carnegie Mellon University. My dissertation examined the plasticity of neural representations during motor skill learning. Before that, I studied recurrent networks and causal inference at CMU’s logic, computation, and AI masters program. And before that, I spent several great years at McGill in Montreal and researched ecological stability as it relates to biodiversity. CV.
|Dec 19, 2018||Talk “Opportunities and challenges in deep learning” for data science Meetup.|
|Dec 16, 2018||Article on “Modernizing Academic Data Science”|
|Nov 18, 2018||Neural pattern imaging datasets uploaded to openNeuro [dataset1, dataset2].|
|Aug 24, 2018||Attended NeuroHackademy for reproducible data science, materials repo.|
|Apr 20, 2018||Dissertation: “Stability of Neural Representational Geometries”|
|Jan 29, 2018||“Plasticity of neuronal representations” on bioRxiv [data] [ipynb] [manuscript]|
|Jan 17, 2018||“Parallel motor learning networks”, abstract, Cosyne 2018.|
|Nov 15, 2017||“Algorithms supporting skill consolidation” Current Opinion|
|Oct 30, 2017||“Statistical Abuse in Biomedical Research”, slides.|