Justin Beland

Research Area

Bayesian inference; neural network modeling; optimization under uncertainty; high-dimensional optimization; generative modeling

Research Interest

uncertainty quantification; graphical models; scalable machine learning; artificial intelligence; probabilistic numerics

Bio

Justin Beland is an Assistant Professor, Teaching Stream, in the Department of Mechanical & Industrial Engineering at the University of Toronto. He specializes in machine intelligence, deep learning, probabilistic modeling, data science, and optimization under uncertainty. Professor Beland’s teaching philosophy is centered around making complex topics understandable and accessible.

His research focuses on the development of novel approaches to address challenges associated with Bayesian optimization of high-dimensional functions and optimization under uncertainty. Specifically, he investigates how representation learning, function decomposition, dimensionality reduction, Gaussian process modeling, deep neural networks, probabilistic numerics,
and manifold learning can be used to tackle these issues.