Seminar of Dr. Markus Abel

Dr. Markus Abel from Potsdam University, Ambrosys and 4Cast GmbH, Germany, will give a seminar

Dr. Markus Abel will give an informal seminar in our group, next tuesday february 11, 16:30 hs. His expertise is on Machine Learning and data science, which has multiples applications and his presentation should be of interest to many of us.

Explainable Machine Learning Control -- robust control and stability analysis
Dr. Markus Abel from Potsdam University, Ambrosys and 4Cast GmbH, Germany

Recently, the term explainable AI became known as an approach to produce models from artificial intelligence which allow interpretation. Since a long time, there are models of symbolic regression in use that are perfectly explainable and mathematically tractable: in this contribution we demonstrate how to use symbolic regression methods to infer the optimal control of a dynamical system given one or several optimization criteria, or cost functions. In previous publications, network control was achieved by automatized machine learning control using genetic programming. Here, we focus on the subsequent analysis of the analytical expressions which result from the machine learning. In particular, we use AUTO to analyze the stability properties of the controlled oscillator system which served as our model. As a result, we show that there is a considerable advantage of explainable models over less accessible neural networks.