BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210224T150000
DTEND;TZID=America/New_York:20210224T160000
DTSTAMP:20260407T035554
CREATED:20210212T183422Z
LAST-MODIFIED:20210212T183422Z
UID:4245-1614178800-1614182400@seasevents.nmsdev7.com
SUMMARY:CIS Seminar: "Enhancing Usability and Explainability of Data Systems"
DESCRIPTION:The recent growth of data science has expanded its reach to an ever-growing user base of non-experts. Unfortunately\, most existing systems offer limited usability and support for explanations: these systems are usable only by experts with sound technical skills\, and even experts are hindered by the lack of transparency into the inner workings of the systems. My research focuses on solving the challenges users face while interacting with data systems and\, thus\, pushes the frontiers towards achieving democratization of data systems\, demanding that people with different skills and backgrounds should be able to use these data systems alike. Further\, my research aims at providing explainability of the behavior of data systems to help the users understand and trust the system function\, especially when unexpected behavior occurs. In this talk\, I will discuss frameworks that address these challenges in a variety of settings and applications\, including relational data querying\, document summarization\, system debugging\, and trust in machine-learning models that learn from data.
URL:https://seasevents.nmsdev7.com/event/cis-seminar-enhancing-usability-and-explainability-of-data-systems/
LOCATION:Zoom – Email CIS for link\, cherylh@cis.upenn.edu
ORGANIZER;CN="Computer and Information Science":MAILTO:cherylh@cis.upenn.edu
END:VEVENT
END:VCALENDAR