BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
UID:242521
DTSTAMP:20260911T113915Z
DTSTART;TZID=America/New_York:20260917T170000
DTEND;TZID=America/New_York:20260917T180000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/mathematical-sciences
 -department-siam-faculty-talk-professor-randy-paffenroth
SUMMARY:Mathematical Sciences Department SIAM Faculty Talk - Professor Rand
 y Paffenroth
DESCRIPTION:SIAM Faculty Talk - Professor Randy Paffenroth\nThursday, Septe
 mber 17\n5-6 pm\nUnity Hall 500\n\nAbstract: Neural networks (NN), ranging
  from Large Language Models like ChatGPT and Claude to simpler “dense” mod
 els, impact our daily lives in many ways. The underlying mathematical prin
 ciples of such NNs are not universally well understood, and in this talk w
 e will draw connections between NNs and classic mathematical ideas such as
  dynamical systems. NNs can be divided into two broad categories, “recurre
 nt” and “non-recurrent” and both types of Neural Networks are popular and 
 extensively studied. However, these two kinds of algorithms are more close
 ly related than is often appreciated. In this talk we will focus on exampl
 es that are accessible to a wide audience, but also “dip our toes” into de
 eper mathematical waters.\n
END:VEVENT
END:VCALENDAR