March 29, 2017

JSI colloquium of our Department member Prof. dr. Juš Kocijan: Probabilistic kernel method for system identification

On Wednesday, March 29, 2017, our Department member Prof. Dr.Juš Kocijan is presenting at Jožef Stefan Institute Lecture Hall a lecture entitled Probabilistic kernel method for system identification.

From the content:
The Gaussian-process model is an example of a probabilistic, kernel-regression model that can be used for the identification of nonlinear dynamic systems. It possesses several interesting features like model predictions contain the measure of confidence; the model has a small number of optimisation parameters and different possibilities of including prior knowledge. The Gaussian-process approach to modelling alleviates any model bias by not focusing on a single dynamics model, but by using a probabilistic dynamics model, a distribution over all plausible dynamics models that could have generated the observed experience. The framework for the identification of dynamic systems with Gaussian- process models will be presented and illustrated with a case study.

Video lecture: