BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Interpretable Machine Learning for Science - Miles Cranmer\, Princ
 eton University
DTSTART:20221214T155000Z
DTEND:20221214T163000Z
UID:TALK193681@talks.cam.ac.uk
CONTACT:Leona Hope-Coles
DESCRIPTION:Would Kepler have discovered his laws if machine learning had 
 been around in 1609? Or would he have been satisfied with the accuracy of 
 some black box regression model\, leaving Newton without the inspiration t
 o find the law of gravitation? In this talk I will present a review of som
 e industry-oriented machine learning algorithms\, and discuss a major issu
 e facing their use in the natural sciences: a lack of interpretability. I 
 will then outline several approaches I have developed with collaborators t
 o help address these problems\, based largely on a mix of structured deep 
 learning and symbolic learning. I will walk through some applications of t
 hese techniques\, and how we may gain new insights from such results.\n\n\
 n\nLink to lecture:https://teams.microsoft.com/l/meetup-join/19%3ameeting_
 Njg0NzRjMDctYTI4Yy00MzBhLTk0MTItYWMxNmQ1YTYzNjhl%40thread.v2/0?context=%7b
 %22Tid%22%3a%2249a50445-bdfa-4b79-ade3-547b4f3986e9%22%2c%22Oid%22%3a%2219
 7d44f9-a582-408b-b638-108327541246%22%7d\n\n[Please do not select the link
  to the lecture until it is due to start\, thank you.]
LOCATION:Cavendish Laboratory\, Pippard Lecture Theatre &amp\; TEAMS
END:VEVENT
END:VCALENDAR