BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Computer Science - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Computer Science
X-ORIGINAL-URL:https://www.cs.jhu.edu
X-WR-CALDESC:Events for Department of Computer Science
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:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
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
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20201112T110000
DTEND;TZID=America/New_York:20201112T120000
DTSTAMP:20260422T152523
CREATED:20210629T210725Z
LAST-MODIFIED:20210629T210725Z
UID:1962515-1605178800-1605182400@www.cs.jhu.edu
SUMMARY:IAA & CS Seminar Series: Leilani Gilpin\, MIT\, Massachusetts Institute of Technology – “Anomaly Detection through Explanations”
DESCRIPTION:Locationhttp://bit.ly/Leilani-Gilpin Password: 467261AbstractUnder most conditions\, complex systems are imperfect. When errors occur\, as they inevitably will\, systemsneed to be able to (1) localize the error and (2) take appropriate action to mitigate the repercussions of thaterror. In this talk\, I present new methodologies for detecting and explaining errors in complex systems. My novelcontribution is a system-wide monitoring architecture\, which is composed of introspective\, overlapping committeesof subsystems. Each subsystem is encapsulated in a “reasonableness” monitor\, an adaptable framework thatsupplements local decisions with commonsense data and reasonableness rules. This framework is dynamicand introspective: it allows each subsystem to defend its decisions in different contexts: to the committees itparticipates in and to itself. For reconciling system-wide errors\, I developed a comprehensive architecture that Icall “Anomaly Detection through Explanations (ADE).” The ADE architecture contributes an explanation synthesizerthat produces an argument tree\, which in turn can be traced and queried to determine the support of a decision\,and to construct counterfactual explanations. I have applied this methodology to detect incorrect labels in semiautonomous vehicle data\, and to reconcile inconsistencies in simulated\, anomalous driving scenarios.My work has opened up the new area of explanatory anomaly detection\, working towards a vision in which complexsystems will be articulate by design: they will be dynamic; internal explanations will be part of the design criteria;system-level explanations will be provided\, and they can be challenged in an adversarial proceeding.BioLeilani H. Gilpin is a research scientist at Sony AI and a collaborating researcher at MIT CSAIL. Her research focuses on enablingopaque autonomous systems to explain themselves for robust decision-making\, system debugging\, and accountability. Hercurrent work integrates explainability into reinforcement learning.She has a PhD in Computer Science from MIT\, an M.S. in Computational and Mathematical Engineering from StanfordUniversity\, and a B.S. in Mathematics (with honors)\, B.S. in Computer Science (with highest honors)\, and a music minor fromUC San Diego. She is currently co-organizing the AAAI Fall Symposium on Anticipatory Thinking\, where she is the lead of theautonomous vehicle challenge problem. Outside of research\, Leilani enjoys swimming\, cooking\, rowing\, and org-mode.View previous seminars at https://iaa.jhu.edu/event/HostsIAA and CSVideoWatch seminar video.
URL:https://www.cs.jhu.edu/event/iaa-cs-seminar-series-leilani-gilpin-mit-massachusetts-institute-of-technology-anomaly-detection-through-explanations/
END:VEVENT
END:VCALENDAR