Bayesian Deep Learning on a Quantum Computer | TDLS Author Speaking
32Toronto Deep Learning Series, 9 October 2018
For slides and more information, visit https://tdls.a-i.science/events/2018-10-09/
Paper Review: https://arxiv.org/abs/1806.11463
Speaker: Peter Wittek (University of Toronto, Perimeter Institute, Vector Institute, Creative Destruction Lab)
Host: Zero Gravity Labs (ZGL)
Date: Oct 9th, 2018
Bayesian Deep Learning on a Quantum Computer
Bayesian methods in machine learning, such as Gaussian processes, have great advantages compared to other techniques. In particular, they provide estimates of the uncertainty associated with a prediction. Extending the Bayesian approach to deep architectures has remained a major challenge. Recent results connected deep feedforward neural networks with Gaussian processes, allowing training without backpropagation. This connection enables us to leverage a quantum algorithm designed for Gaussian processes and develop a new algorithm for Bayesian deep learning on quantum computers. The properties of the kernel matrix in the Gaussian process ensure the efficient execution of the core component of the protocol, quantum matrix inversion, providing an at least polynomial speedup over the classical algorithm. Furthermore, we demonstrate the execution of the algorithm on contemporary quantum computers and analyze its robustness with respect to realistic noise models.