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
Original language | English |
---|---|
Title of host publication | The 22nd International Conference on Artificial Intelligence and Statistic |
Pages | 1-15 |
Number of pages | 16 |
Volume | 89 |
Publication status | Published - Apr 2019 |
MoE publication type | A4 Article in a conference publication |
Event | International Conference on Artificial Intelligence and Statistics - Naha, Japan Duration: 16 Apr 2019 → 18 Apr 2019 Conference number: 22 |
Publication series
Name | Proceedings of Machine Learning Research |
---|---|
Publisher | PMLR |
Volume | 89 |
ISSN (Electronic) | 2640-3498 |
Conference
Conference | International Conference on Artificial Intelligence and Statistics |
---|---|
Abbreviated title | AISTATS |
Country | Japan |
City | Naha |
Period | 16/04/2019 → 18/04/2019 |
Keywords
- gaussian process
- Bayesian methods