BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:The Next Great Scientific Theory is Hiding Inside a Neural Network
DTSTART:20240403T220000Z
DTEND:20240403T230000Z
DTSTAMP:20260614T140200Z
UID:indico-event-3947@indico.flatironinstitute.org
DESCRIPTION:The Next Great Scientific Theory is Hiding Inside a Neural Net
 workContact: plund@simonsfoundation.org\; lectures@simonsfoundation.orgR
 egistration link: https://www.eventbrite.com/e/the-next-great-scientific-t
 heory-is-hiding-inside-a-neural-network-tickets-868355955037Machine learni
 ng methods such as neural networks are quickly finding uses in everything 
 from text generation to construction cranes. Excitingly\, those same tools
  also promise a new paradigm for scientific discovery.In this Presidential
  Lecture\, Miles Cranmer will outline an innovative approach that leverage
 s neural networks in the scientific process. Rather than directly modeling
  data\, the approach interprets neural networks trained using the data. Th
 rough training\, the neural networks can capture the physics underlying th
 e system being studied. By extracting what the neural networks have learne
 d\, scientists can improve their theories. He will also discuss the Polyma
 thic AI initiative\, a collaboration between researchers at the Flatiron I
 nstitute and scientists around the world. Polymathic AI is designed to spu
 r scientific discovery using similar technology to that powering ChatGPT. 
 Using Polymathic AI\, scientists will be able to model a broad range of ph
 ysical systems across different scales.About the Speaker:Cranmer is an ass
 istant professor in data intensive science at the University of Cambridge 
 with joint appointments in the Department of Applied Mathematics and Theor
 etical Physics and the Institute of Astronomy. He completed his Ph.D. at P
 rinceton University. His research focuses on accelerating scientific disco
 very by developing and applying novel methods at the intersection of machi
 ne learning and physics. Cranmer has created a suite of standard software 
 libraries for ‘symbolic regression’ that have been utilized in numerou
 s scientific discoveries. His work covers various areas of deep learning\,
  including physics-motivated architectures such as Lagrangian neural netwo
 rks.SCHEDULEDoors open: 5:30 p.m. (No entrance before 5:30 p.m.)Lecture: 
 6:00 p.m.–7:00 p.m. (Admittance closes at 6:20 p.m.)Inquiries: lectures
 @simonsfoundation.org\n\nhttps://indico.flatironinstitute.org/event/3947/
LOCATION:Gerald D. Fischbach Auditorium/2-GDFA (160 5th Avenue)
URL:https://indico.flatironinstitute.org/event/3947/
END:VEVENT
END:VCALENDAR