BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 21.0.11
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:20230425T141327
UID:959455f0-e362-11ed-96a6-000e0c3db68b
SUMMARY:Vortrag von Prof. Ian Manchester
DESCRIPTION:Prof. Ian Manchester\nProfessor of Mechatronic Engineering\nThe University of Sydney\nSydney, Australia\n  \nTuesday 2023-05-02 9:30 a.m.\nIST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen  \nAbstract\nIn this talk, we will introduce a new approach to building neural networks and nonlinear\ndynamical models with built-in guarantees of stability, robustness and other certified behavioural\nproperties. We will trace the connections between convex parameterizations from robust control to\nso-called “direct” parameterizations, i.e. smooth & unconstrained parameterisations of all\nmodels that satisfy prescribed conditions. These direct parameterizations enable learning of robust\nstatic and dynamic models via simple first-order methods, without any auxiliary constraints or\nprojections. We will explore some applications in certifiably-robust image classification,\nphysics-informed learning of contracting nonlinear observers, and robust reinforcement learning for\nnonlinear partially-observed systems.  \nBiographical Information\nIan R. Manchester received the B.E. and Ph.D. degrees in electrical engineering from the\nUniversity of New South Wales, Sydney, NSW, Australia, in 2002 and 2006, respectively. From\n2006-2009 he was a post-doctoral researcher at Umea University, Sweden, and from 2009-2012 he was a\nResearch scientist at the Massachusetts Institute of Technology. Since 2012 he has been a faculty\nmember at the University of Sydney, Australia, where he is currently Professor of Mechatronic\nEngineering, Director of the Australian Centre for Robotics, and Director of the Australian Robotic\nInspection & Asset Management Hub. His current research interests are in algorithms for\ncontrol, estimation, and learning of nonlinear dynamical systems, with applications in robotics,\nrobust machine learning, biomedical engineering, and smart networked systems. \n   
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20230502
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/de/veranstaltungen/Vortrag-von-Prof.-Ian-Manchester/
END:VEVENT
END:VCALENDAR