Gaussian processes with neural network inductive biases for fast domain adaptation

Add to your list(s) Download to your calendar using vCal

• Andreas Damianou (Amazon)
• Friday 28 February 2020, 17:30-19:00
• Auditorium, Microsoft Research Ltd, 21 Station Road, Cambridge, CB1 2FB.

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

Recent advances in learning algorithms for deep neural networks allows us to train such models efficiently to obtain rich feature representations. However, when it comes to transfer learning, local optima in the high-dimensional parameter space still pose a severe problem. Motivated by this issue, we propose a framework for performing probabilistic transfer learning in the function space while, at the same time, leveraging the rich representations offered by deep neural networks. Our approach consists of linearizing neural networks to produce a Gaussian process model with covariance function given by the network’s Jacobian matrix. The result is a closed-form probabilistic model which allows fast domain adaptation with accompanying uncertainty estimation.

This talk is part of the AI+Pizza series.

This talk is included in these lists:

• AI+Pizza
• Auditorium, Microsoft Research Ltd, 21 Station Road, Cambridge, CB1 2FB
• bld31

Note that ex-directory lists are not shown.