BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260619T054200EDT-18649J38u4@132.216.98.100
DTSTAMP:20260619T094200Z
DESCRIPTION:Department of Electrical and Computer Engineering Seminar\n	\n	Sp
 eaker: Steffen Schneider\n	International Max Planck Research School for Int
 elligent Systems in Tuebingen and EPFL\n	\n	Abstract: A fundamental goal in 
 science is understanding complex relationships of biological systems acros
 s scales and time. Modern life science research is enabling data collectio
 n at a rapid pace and at increasing scale\, yet our ability to understand 
 complex systems and reason about their underlying dynamics is still limite
 d. To this end\, my work has focused on developing new machine learning to
 ols for inferring latent structure from the data we observe. In my talk\, 
 I will primarily focus on new work developing a variant of contrastive lea
 rning suitable for scientific inference (CEBRA). As an example\, I will hi
 ghlight the algorithm’s ability to uncover consistent and robust neural la
 tent dynamics. Lastly\, I will discuss theoretical foundations for such mo
 dels\, and discuss my prior work in speech and vision\, specifically regar
 ding data efficiency and model robustness.\n	Biography: Steffen Schneider i
 s a final year ELLIS PhD student in Machine Learning and Computational Neu
 roscience at the International Max Planck Research School for Intelligent 
 Systems in Tuebingen and at EPFL in Geneva. His PhD work is supported by a
  Google PhD Fellowship and revolves around robust deployment of machine le
 arning models and self-supervised learning for scientific data analysis. M
 r. Schneider has also worked on large scale machine learning for speech\, 
 vision and language with research visits at FAIR/Meta AI in Menlo Park/NYC
 \, and on object-centric learning at Amazon in Tuebingen. Beyond research\
 , he co-founded the edtech/science communication startup “KI macht Schule”
  to teach AI in schools.\n
DTSTART:20230306T150000Z
DTEND:20230306T160000Z
LOCATION:MC 603\, McConnell Engineering Building\, CA\, QC\, Montreal\, H3A
  0E9\, 3480 rue University
SUMMARY:Closing the identifiability gap: Interpretable and reproducible sci
 entific inference across modalities\, scales and time
URL:/cim/channels/event/closing-identifiability-gap-in
 terpretable-and-reproducible-scientific-inference-across-modalities-351762
END:VEVENT
END:VCALENDAR