Intelligent behaviour fascinates me: how animals can efficiently process a flood of sensory signals and learn to take actions to survive. Nature has produced elegant solutions for information processing that I believe can help us tackle challenges in modern society. I am passionate about taking what we know from how brains process information, to making intelligent machines.

My work in the Bayesian Intelligent Autonomous Systems lab focuses on computational efficiency. Internally, an agent must trade off the costs of performing a computation with prediction accuracy. Higher efficiency will allow us to deploy agents for more complicated tasks, such as long-term motor planning, safe autonomous driving and optimal search using drone swarms.

Most of my previous projects revolve around sampling bias in machine learning. Mainly, I designed robust estimators for statistical models, which have been applied to image, signal and natural language processing problems.