Gaussian processes techniques for non-linear multidimensional dynamical systems

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

• Wil Ward (University of Sheffield)
• Tuesday 24 November 2020, 15:00-16:00
• https://zoom.us/j/3264147316?pwd=S1ZZMS81UzRjRnp3NlFTcWFPOVpnZz09.

If you have a question about this talk, please contact Hong Duong.

Gaussian processes are a highly-effective Bayesian non-parametric tool for performing non-linear regression, including in multivariate systems. However in systems where there are dependent variables interacting non-linearly, or where the dynamics of the system are non-linear, Gaussian processes are no longer a representative function prior. This talk introduces recent developments in using Gaussian processes in approximations for different non-linear systems, including those with non-linear interactions between different output dimensions, and non-linear differential equations with partially known dynamics, such as those with hidden forcing terms, as seen in control systems.

This talk is part of the Data Science and Computational Statistics Seminar series.

This talk is included in these lists:

• Analysis Seminar
• Data Science and Computational Statistics Seminar
• School of Mathematics Events
• https://zoom.us/j/3264147316?pwd=S1ZZMS81UzRjRnp3NlFTcWFPOVpnZz09

Note that ex-directory lists are not shown.