BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:AI Meets Theoretical Physics - Dr Sven-Ludwig Krippendorf (Physics
 /DAMTP)
DTSTART:20241121T140000Z
DTEND:20241121T150000Z
UID:TALK223921@talks.cam.ac.uk
CONTACT:Sri Aitken
DESCRIPTION:In this talk I present an overview of our work at the intersec
 tion of theoretical physics and machine learning. This is to outline how w
 e can use ML to automatize the pen and paper methods of theoretical physic
 ists. I present some examples on this journey which include: 1) Utilizing 
 the unreasonable effectiveness of mathematics we can identify analytical e
 xpressions for symmetries of a system. 2) Formulating the search for solut
 ions to partial differential equations as an optimization problem\, we get
  an unprecedented look into Calabi-Yau metrics. 3) Rendering efficient num
 erical tools to study the physics of string theory models using automatic 
 differentiation\, vectorization and just in time compilation. In the secon
 d part of the talk I give an overview on how we get insights into the dyna
 mics of neural network using collective variables.
LOCATION:Maxwell Centre
END:VEVENT
END:VCALENDAR