Speaker: Peter Wittek (University of Toronto, Canada)
Title: Quantum-enhanced machine learning and AI
Abstract: Quantum technologies are maturing: we see more and more applications of quantum information processing and the recent progress in building scalable universal quantum computers is remarkable. The pace of development is akin to the rapid advances made in machine learning by deep architectures. It is natural to ask whether quantum resources could boost learning algorithms: this field of enquiry is called quantum-enhanced machine learning. Recent progress indicates that current and near-future quantum technologies have tangible benefits for machine learning. The same way massively parallel computing infrastructure enabled deep learning, quantum technologies are set to become part of the computational toolbox, addressing learning algorithms that do not lend themselves to backpropagation and stochastic gradient descent. The most immediate targets are approximate probabilistic inference in graphical models, discrete and highly non-convex objective functions, and problems t
hat can be mapped to solving linear equations. In this talk, we give an overview of the key research directions and implementations that may lead to applications in the near future.
|Date||June 12, 2017 (Mon) 16:30 - 18:00|