BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UNIFY
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:https://events.ucf.edu/event/3528472/mathematics-colloquium-by-dr-hongkai-zhao-duke-university/
DTSTAMP:20241021T153000
DTSTART:20241021T153000
DTEND:20241021T163000
LOCATION:MSB 318: Mathematical Sciences Building, Room 318
SUMMARY:Mathematics Colloquium by Dr. Hongkai Zhao, Duke University
URL:https://events.ucf.edu/event/3528472/mathematics-colloquium-by-dr-hongkai-zhao-duke-university/
DESCRIPTION:The UCF [Mathematics Colloquium](https://sciences.ucf.edu/math/colloquium/), held every Monday from 3:30pm to 4:30pm in MSB 318, offers a diverse platform for research scholars, faculty, students, and industry experts to share and exchange ideas, fostering discussion and networking across various areas of mathematics.\n\nDr. [Hongkai Zhao](https://scholars.duke.edu/person/Hongkai.Zhao), Ruth F. DeVarney Professor from Duke University, will speak at this week's colloquium on "Mathematical and Numerical Understanding of Neural Networks: From Representation to Learning Dynamics."\n\nAbstract: In this talk I will present both mathematical and numerical analysis as well as experiments to study a few basic computational issues in using neural network to approximate functions: (1) the stability and accuracy, (2) the learning dynamics and computation cost, and (3) structured and balanced approximation. These issues are investigated for both approximation and optimization in asymptotic and non-asymptotic regimes.
END:VEVENT
END:VCALENDAR