Bio
My work is motivated by a general interest in building more flexible, adaptive computational systems. This has led to research in a range of different areas, including computational neuroscience, (hierarchical) reinforcement learning, and deep learning. Now I work to build software that combines these (and other) approaches, creating products that translate research advances into real world applications.
Current work
I am currently the ML/Compiler Team Lead and a Senior Staff Machine Learning Engineer at Applied Brain Research, a company I co-founded with other members of the Computational Neuroscience Research Group in 2014. My work focuses on taking our research in low power AI and building it into products that make those complex methods accessible to non-expert users.
Education
-
Postdoctoral Associate
Supervisor: Matthew Botvinick
Princeton University, USA -
PhD, Computer Science (Theoretical Neuroscience)
Thesis: Hierarchical reinforcement learning in a biologically plausible
neural architecture
Supervisor: Chris Eliasmith
University of Waterloo, Canada -
MMath, Computer Science (Theoretical Neuroscience)
Thesis: A neural modelling approach to investigating general intelligence
Supervisor: Chris Eliasmith
University of Waterloo, Canada -
BA, Computer Science and Philosophy
Mount Allison University, Canada
