Deep Gaussian Processes

[edit]

at KTH Royal Institute of Technology, Sweden on Apr 30, 2015 [pdf]
Neil D. Lawrence, University of Sheffield

Abstract

In this talk we describe how deep neural networks can be modified to produce deep Gaussian process models. The framework of deep Gaussian processes allow for unsupervised learning, transfer learning, semi-supervised learning, multi-task learning and principled handling of different data types (count data, binary data, heavy tailed noise distributions). The main challenge is to handle the intractabilities. In this talk we review the variational bounds that are used under the framework of variational compression and give some initial results of deep Gaussian process models.

Links