BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 21.0.27
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700329T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701025T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241023T163226
UID:9fc1fdd6-914b-11ef-a46e-000e0c3db68b
SUMMARY:Talk of Prof. Alberto Bemporad
DESCRIPTION:Prof. Alberto Bemporad\nIMT School for Advanced Studies Lucca\nLucca, Italy\n\n  \nTuesday 2024-10-29 3 p.m.\nIST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen  \nAbstract\nMachine learning has gained immense popularity in various fields, including control, due to its\nability to extract mathematical models from data. In my talk, I will present different machine\nlearning techniques that can aid in designing and calibrating model predictive control (MPC) laws.\nI will present different batch and incremental methods tailored for the identification of nonlinear\nstate-space models, such as recurrent neural networks, possibly under nonsmooth L1 and group-Lasso\npenalties. I will show evidence that these methods, which are related to the family of quasi-Newton\noptimization algorithms, tend to outperform popular gradient-descent methods. Moreover, I will\ndiscuss the use of incremental learning methods to train disturbance models and achieve offset-free\ntracking in nonlinear MPC. Finally, I will present global and preference-based optimization\ntechniques that rely on surrogate functions to actively learn the optimal MPC parameters. Biographical Information\nAlberto Bemporad received his Ph.D. in Control Engineering in 1997 from the University of\nFlorence, Italy. In 1996/97 he was with the Center for Robotics and Automation, Department of\nSystems Science & Mathematics, Washington University, St. Louis. In 1997-1999 he held a\npostdoctoral position at the Automatic Control Laboratory, ETH Zurich, Switzerland, where he\ncollaborated as a Senior Researcher until 2002. In 1999-2009 he was with the Department of\nInformation Engineering of the University of Siena, Italy, becoming an Associate Professor in 2005.\nIn 2010-2011 he was with the Department of Mechanical and Structural Engineering of the University\nof Trento, Italy. Since 2011 he has been a Full Professor at the IMT School for Advanced Studies\nLucca, Italy, where he served as the Director of the institute from 2012 to 2015. He spent visiting\nperiods at Stanford University, the University of Michigan, and Zhejiang University. In 2011 he\nco-founded ODYS S.r.l., a company specialized in developing model predictive control systems for\nindustrial production. He is the author or coauthor of various software packages for model\npredictive control design and implementation, including the Model Predictive Control Toolbox (The\nMathworks, Inc.) and the Hybrid Toolbox for MATLAB, and is the co-inventor of 21 patents. He was an\nAssociate Editor of the IEEE Transactions on Automatic Control during 2001-2004 and Chair of the\nTechnical Committee on Hybrid Systems of the IEEE Control Systems Society from 2002 to 2010. He\nreceived the IFAC High-Impact Paper Award for the 2011-14 triennial, the IEEE CSS Transition to\nPractice Award in 2019, the 2021 SAE Environmental Excellence in Transportation Award, the 2024\nBeale–Orchard-Hays Prize for Excellence in Computational Mathematical Programming, the Control\nEngineering Practice 2024 Best Paper Award, and an ERC Advanced Research Grant in 2024. He has been\nan IEEE Fellow since 2010.\n\n\n\n 
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20241029
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/events/Talk-of-Prof.-Alberto-Bemporad/
END:VEVENT
END:VCALENDAR