ai seminar – johannes günther

  • University of Alberta CSC 3-33 Edmonton, AB Canada

machine learning applied to real-world problems

This talk provides a viewpoint into natural ways that machine learning can be applied to industrial control problems. As a first example, machine learning is used to enhance a simple classical control system---a PID controller in this case---to extend its capabilities. In a second example, a complex laser welding process is augmented with representation prediction, and control learning. Specific machine learning algorithms discussed in this talk include: Deep Learning, General Dynamic Neural Networks and methods from Reinforcement Learning such as General Value Functions and Actor-Critic RL. Specifically, it will be shown how Deep Learning and Reinforcement Learning can be combined into an intelligence-like architecture to control complex industrial applications.

Bio: Johannes Günther studied mechanical engineering at the TU Darmstadt and Stuttgart. He received his Degree (Dipl.-Ing.) in 2012 from the University in Stuttgart. During his studies he worked as an intern at the Dr. Ing. h.c.F. Porsche AG and the Fraunhofer Institute. Since 2012 he has worked as a PhD candidate at TU München with Prof. Dr.-Ing. Klaus Diepold, the Chair of Data Processing, within the Department of Electrical Engineering and Information Processing. Johannes's research focus is applied machine learning. He has also delivered lectures in ‘data analysis for computer engineering’ and ‘time-varying systems and computations’.


ai seminar series

Fridays at noon, Amii and the Department of Computing Science host AI Seminars, engaging presentations on topics in the broad field of artificial intelligence. With speakers from the University of Alberta and other world-leading groups, the talks give AI enthusiasts a friendly way of engaging with the latest trends and topics in research and development.

Seminars are open to the public, and no registration is required, though seating is limited and on a first-come-first-served basis. Topics range from foundational theoretical work to innovative applications of artificial intelligence technologies.

If you would like to present at an upcoming AI Seminar, please contact Colin Bellinger.

Join the AI Seminar mailing list to stay up-to-date on all the latest presentations.