BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260717T125845EDT-4872C6uB85@132.216.98.100
DTSTAMP:20260717T165845Z
DESCRIPTION:Title:  The (symmetric) Ising Perceptron\n\nAbstract. The Perce
 ptron model was proposed as early as the 1950's as a toy model of a one-la
 yer neural network. The basic model consists of a set of solutions (either
  the Hamming cube or the sphere of dimension n) and a set of constraints g
 iven by independent n-dimensional Gaussian vectors. The constraints are th
 at the inner product of a solution vector with each constraint vector scal
 ed by sqrt{n} must lie in some interval on the real line. Probabilistic qu
 estions about the model include the satisfiability threshold (or the 'stor
 age capacity') and questions about the typical structure of the solution s
 pace. Algorithmic questions include the tractability of finding a solution
  (the learning problem in the neural network interpretation). I will descr
 ibe the model\, the main problems\, and recent progress.\n\nZoom: https://
 mcgill.zoom.us/j/82167352773?pwd=VHZPZWQ0d1g1S3M0cnVvWW9jbWxEdz09\n
DTSTART:20221208T163000Z
DTEND:20221208T173000Z
LOCATION:Room 1214\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Will Perkins (Georgia Tech)
URL:https://www.mcgill.ca/mathstat/channels/event/will-perkins-georgia-tech
 -344077
END:VEVENT
END:VCALENDAR