BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Center for Innovation through Visualization and Simulation (CIVS) - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Center for Innovation through Visualization and Simulation (CIVS)
X-ORIGINAL-URL:https://www.pnw.edu/civs
X-WR-CALDESC:Events for Center for Innovation through Visualization and Simulation (CIVS)
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20240310T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20241103T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20250309T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20251102T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20260308T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20261101T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20270314T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20271107T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20260213T143000
DTEND;TZID=America/Chicago:20260213T153000
DTSTAMP:20260628T184316
CREATED:20260205T174152Z
LAST-MODIFIED:20260205T174152Z
UID:10000031-1770993000-1770996600@www.pnw.edu
SUMMARY:Smarter Grids Through Deeper Learning
DESCRIPTION:Spatiotemporal Graph Models for Distribution Systems\nModern power-distribution systems are becoming increasingly complex due to widespread integration of distributed-energy resources and the need for fast\, reliable fault detection. This talk explores recent advances in graph-based deep learning for power systems\, which model networks as spatiotemporal graphs to capture both spatial structure and measurement dynamics. \nFocusing on deep sparse spatiotemporal generative models\, including graph convolutional autoencoders and generative architectures\, the talk highlights applications such as fault classification and location in distribution systems and behind-the-meter load and photovoltaic disaggregation. Experimental results show substantial performance gains over existing state-of-the-art methods.
URL:https://www.pnw.edu/civs/event/smarter-grids-through-deeper-learning/
CATEGORIES:College of Engineering and Sciences,University Calendar,University College Calendars
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20251114T143000
DTEND;TZID=America/Chicago:20251114T153000
DTSTAMP:20260628T184316
CREATED:20251112T223256Z
LAST-MODIFIED:20251112T223615Z
UID:10000030-1763130600-1763134200@www.pnw.edu
SUMMARY:"Towards Robust & Secure AI Agents in Open-World" with Professor Shafkat Islam
DESCRIPTION:Computer Science and CIVS Distinguished Speaker Seminar \nEnsuring secure and robust AI agents in open-world environments is vital to counter emerging cyber threats. This talk presents three research directions: \n\nan environment-agnostic\, evidence-based framework for assessing AI robustness\,\nanalysis and defense against triggerless backdoor attacks in federated learning\, and\norchestration and monitoring strategies for resilient\, fault-tolerant computation in heterogeneous platforms.\n\nMeet the Speaker\nShafkat Islam \nAssistant Professor of Computer Science \nShafkat Islam is an assistant professor and the director of the Trustworthy\, Robust & Secure Intelligent Systems (TRUST-IT) lab in the computer science department at Purdue University Northwest.
URL:https://www.pnw.edu/civs/event/towards-robust-secure-ai-agents-in-open-world-with-professor-shafkat-islam/
CATEGORIES:College of Engineering and Sciences,University Calendar,University College Calendars
END:VEVENT
END:VCALENDAR