BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000605Z
LOCATION:DEF Concourse
DTSTART;TZID=America/Denver:20231116T100000
DTEND;TZID=America/Denver:20231116T170000
UID:submissions.supercomputing.org_SC23_sess300_spostu115@linklings.com
SUMMARY:A Comparison of Deep and Shallow Residual Networks for Medical Ima
 ging Classification
DESCRIPTION:Elaine Lu (Columbia University)\n\nThe complexity and paramete
 rs of mainstream large models are increasing rapidly. For example, the inc
 reasingly popular large language models (e.g., ChatGPT) have billions of p
 arameters. While this has led to performance improvements, the performance
  gains for simple tasks may be unacceptable for the additional cost. We ap
 ply residual networks of three different depths and evaluate them extensiv
 ely on the MedMNIST pneumonia dataset. Experimental results show that smal
 ler models can achieve satisfactory performance at significantly lower cos
 ts than larger models.\n\nRegistration Category: Tech Program Reg Pass, Ex
 hibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR