Speaker: Patrick Kidger, Mathematician at Google X
Abstract: This is a quick introduction to neural ODEs for scientific applications. The goal is to (a) provide a modelling tool that enhances the expressivity of existing theory-driven approaches, (b) demonstrate that neural ODEs are easy to use via modern autodifferentiable software, and (c) give enough of the tips-and-tricks needed to make neural ODEs work in practice!
Bio: Patrick studies ML-for-biology, and is best known publicly for (a) developing the field of neural differential equations (neural ODEs, neural SDEs, …), and (b) creating an open-source JAX scientific ecosystem (Equinox, Diffrax, …). The former happened as part of his PhD at Oxford; the latter during his time at Google X.
Zoom Link: https://upenn.zoom.us/j/96060692429