Abstract: Algorithmic progress in machine learning and the ubiquitous availability of powerful infrastructure have opened up the way to leverage optimization potentials in various industrial environments. Rigorous analysis of structured mass data from production facilities highlights deficits that have hidden among the majority of well-behaving processes. This for example allows enterprises to optimize the provisioning of spare parts in large facilities or minimize logistics costs. We show several applications of AI in industry and discuss their impact on the respective business and production processes.
Short Bio: Mathias Bauer was one of the first researchers of the German Research Center for AI (DFKI). He is a DFKI Research Fellow. Since 2001 he founded a number of startups dealing with aspects of data analytics and machine learning. The last of these companies – KIANA Systems – was acquired by KPMG in 2018. Since then, Mathias is a partner in the German Lighthouse, the KPMG Center of Excellence for Data and Analytics, where he is the head of the Advanced Analytics department.
Pavel Potocek Thermo Fisher Scientific Eindhoven, The Netherlands
Abstract: Nowadays Electron Microscopy plays a key role to progress the domain of life science and material science. For example, understanding the connectivity in the brain is a research area that lately receives a lot of attention. Key factors in this research are fast and optimal (good contrast) acquisition of large volume data and later being able to understand the structure. This presentation shows some of the possible key contributions we already see from techniques related to Deep Learning and Neural Networks. The main presented areas are related to super-resolution techniques, particle detection for SPA, Compressive Sensing reconstruction and image segmentation.
Short Bio: Pavel Potocek received his RNDr. in Low temperature plasma in 1984 from Charles University, Prague. He joined originally Philips Electron Optics in 1998, which is Thermo Fisher Scientific now, working in Advanced Technologies group. The main area of professional interest is the beam control and image processing.
Abstract: This talk will be about how artificial intelligence technologies can help to make robotics and industrial processes more autonomous and intelligent. In more detail, we will talk about work at KUKA Corporate Research, where we try to let robots learn tasks by themselves through deep reinforcement learning and how we can detect failure events by using machine learning algorithms.
Short Bio: Manuel Kaspar received his Master of Science in Computer Engineering in 2017 from the University of Augsburg. In 2017 he joined the KUKA Group as a developer in the Cluster Smart Data and Infrastructure concerned with Machine Learning in robotics. Additionally, he received a Bachelor of Arts in philosophy in 2014 from the Hochschule für Philosophie in Munich.
Abstract: The production chain at Saarstahl involves a multitude of specialized and complex metallurgical manufacturing processes and is characterized by uncertainties, changes in customer orders and is subject to various possibilities for discrepancies during production. Such a complicated manufacturing process requires advanced techniques for realizing further improvements. And thus offers an opportunity for using data to predict uncertainties and make decisions which adjust processes. We will show some projects where machine learning was able to improve use cases at Saarstahl AG.
Short Bio: Michael Schäfer is a Senior Software Engineer and Data Scientist at Saarstahl AG. In that role he is responsible for the Data Science & AI group. He has a background in distributed computing systems, system architecture and data science. In 2010 he received a master’s degree in computer science. Michael currently works on machine learning with an emphasis on deep learning.
