Patrick Pilarski is a Canada Research Chair in Machine Intelligence for Rehabilitation revolutionizing the use of artificial intelligence in medical science.
Using a branch of AI called reinforcement learning, Pilarski and his team at the Bionic Limbs for Improved Natural Control (BLINC) Lab at the University of Alberta are using machine learning to build up the intuition or the "predictive ability" of prosthetic limbs, and ultimately improve a person's use of their artificial arm or hand.
"There are a lot of things we hope our bionic parts will do for users-and at present it's really, really hard for a user to control the system to do these things," said Pilarski. "By allowing the machine to learn what the person wants, when they want it and when they need it, it can fill in the gaps for the user; machine learning can be the glue that connects the person with the machine."
Apart from his work at BLINC, Pilarski is also one member of an elite team of Edmonton computing scientists who head up the first branch outside the UK of leading AI research company DeepMind. Pilarski and the team at DeepMind Alberta are doing important work in the area of reinforcement learning-a set of algorithms that allow machines to maximize their performance by automatically determining the ideal behaviour in a specific context.