English

Deep learning with differential Gaussian process flows

Machine Learning 2018-10-16 v2 Machine Learning

Abstract

We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks

Keywords

Cite

@article{arxiv.1810.04066,
  title  = {Deep learning with differential Gaussian process flows},
  author = {Pashupati Hegde and Markus Heinonen and Harri Lähdesmäki and Samuel Kaski},
  journal= {arXiv preprint arXiv:1810.04066},
  year   = {2018}
}