BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Maxime Bergeron (Riskfuel) DTSTART:20210329T190000Z DTEND:20210329T200000Z DTSTAMP:20260423T005647Z UID:YUAAS/28 DESCRIPTION:Title: H ilbert\, Deep Neural Nets and Empirical Moduli Spaces\nby Maxime Berge ron (Riskfuel) as part of York University Applied Algebra Seminar\n\n\nAbs tract\nThe motivation behind Hilbert's 13th problem is often overlooked. I n his original statement\, he opens with: "nomography deals with the probl em of solving equations by means of drawing families of curves depending o n an arbitrary parameter". The question he posed sought to identify a fami ly of functions amenable to such graphical solvers that were essential too ls of his time. More formally\, he asked if it was possible to solve algeb raic equations in terms of towers of algebraic functions of a single param eter. While the question in its original form remains open to this day\, i n the continuous realm it turns out that there is no such thing as a truly multivariate function. In this talk\, we will see how these ideas fit int o the modern deep learning framework\, forming a bridge between algebra an d analysis.\n LOCATION:https://researchseminars.org/talk/YUAAS/28/ END:VEVENT END:VCALENDAR