BEGIN:VCALENDAR
METHOD:PUBLISH
PRODID:www-math-fau-de//Events//DE
VERSION:2.0
BEGIN:VEVENT
SUMMARY:Machine Learning and Dynamical Systems meet in Reproducing Ker
 nel Hilbert Spaces (B. Hamzi\, Imperial College London\, UK)
UID:fad9ce7a-2e12-42ee-86fc-049fb07d28a3
DESCRIPTION:Machine Learning and Dynamical Systems meet in Reproducing
  Kernel Hilbert Spaces Speaker: Prof. Dr. Boumerdiene Hamzi Affiliatio
 n: Imperial College London\, UK Zoom link: Meeting ID: 622 8750 3786 \
 , Passcode: 351356 Abstract: Since its inception in the 19th century t
 hrough the efforts of Poincaré and Lyapunov\, the theory of dynamical
  systems addresses the qualitative behaviour of dynamical systems as u
 nderstood from models. From this perspective\, the modeling of dynamic
 al processes in applications requires a detailed understanding of the 
 processes to be analyzed. This deep understanding leads to a model\, w
 hich is an approximation of the observed reality and is often expresse
 d by a system of Ordinary/Partial\, Underdetermined (Control)\, Determ
 inistic/Stochastic differential or difference equations. While models 
 are very precise for many processes\, for some of the most challenging
  applications of dynamical systems (such as climate dynamics\, brain d
 ynamics\, biological systems or the financial markets)\, the developme
 nt of such models is notably difficult. On the other hand\, the field 
 of machine learning is concerned with algorithms designed to accomplis
 h a certain task\, whose performance improves with the input of more d
 ata. Applications for machine learning methods include computer vision
 \, stock market analysis\, speech recognition\, recommender systems an
 d sentiment analysis in social media. The machine learning approach is
  invaluable in settings where no explicit model is formulated\, but me
 asurement data is available. This is frequently the case in many syste
 ms of interest\, and the development of data-driven technologies is be
 coming increasingly important in many applications. The intersection o
 f the fields of dynamical systems and machine learning is largely unex
 plored and the objective of this talk is to show that working in repro
 ducing kernel Hilbert spaces offers tools for a data-based theory of n
 onlinear dynamical systems. In this talk\, we introdu
DTSTART:20210623T093000Z
DTEND:20210623T103000Z
LOCATION:Online
DTSTAMP:20260730T161056Z
END:VEVENT
END:VCALENDAR