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:20260422T000603Z
LOCATION:DEF Concourse
DTSTART;TZID=America/Denver:20231115T100000
DTEND;TZID=America/Denver:20231115T170000
UID:submissions.supercomputing.org_SC23_sess299_spostu107@linklings.com
SUMMARY:Road To Reliability:  Optimizing Self-Driving Consistency With Rea
 l-Time Speed Data
DESCRIPTION:William Fowler (Tufts University)\n\nSelf-driving cars can pot
 entially improve transportation efficiency and reduce human fatalities – p
 rovided they have access to significant processing power and large amounts
  of data. One popular approach for actualizing autonomous vehicles is usin
 g end-to-end learning, in which a machine learning model is trained on a l
 arge data set of real human driving. This poster shows how self-driving co
 nsistency can be improved using a Convolutional Neural Network (CNN) to pr
 edict current velocity. Our approach first reproduces an end-to-end learni
 ng result and then extends it with real-time speed data as additional mode
 l input.\n\nTag: Artificial Intelligence/Machine Learning, Algorithms, App
 lications, Architecture and Networks, Cloud Computing, Distributed Computi
 ng, Data Analysis, Visualization, and Storage, Performance Measurement, Mo
 deling, and Tools, Programming Frameworks and System Software\n\nRegistrat
 ion Category: Tech Program Reg Pass, Exhibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR