BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CECS - ECPv6.18.4//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.cecs.uci.edu
X-WR-CALDESC:Events for CECS
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20230312T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20231105T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20240310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20241103T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20240123T120000
DTEND;TZID=America/Los_Angeles:20240123T130000
DTSTAMP:20240502T211540Z
CREATED:20240502T211540Z
LAST-MODIFIED:20240502T211540Z
UID:16263-1706011200-1706014800@www.cecs.uci.edu
SUMMARY:Provably-Safe Offloading of Neural Network Controllers for Energy-Efficiency in Autonomous Driving Systems
DESCRIPTION:Title: Provably-Safe Offloading of Neural Network Controllers for Energy-Efficiency in Autonomous Driving Systems \nSpeaker: Mohanad Odema \nDate and Time: Tuesday\, January 23rd\, 12:00pm \nLocation: EH 2430 \nAbstract: \nTo mitigate the high energy demand of Neural Network (NN) based Autonomous Driving Systems (ADSs)\, we consider the problem of offloading NN controllers from the ADS to nearby edge-computing infrastructure\, but in such a way that formal vehicle safety properties are guaranteed. In particular\, we propose the EnergyShield framework\, which repurposes a controller “shield” as a low-power runtime safety monitor for the ADS vehicle. Specifically\, the shield in EnergyShield provides not only safety interventions but also a formal\, state-based quantification of the tolerable edge response time before vehicle safety is compromised. Using EnergyShield\, an ADS can then save energy by wirelessly offloading NN computations to edge computers\, while still maintaining a formal guarantee of safety until it receives a response (on-vehicle hardware provides a just-in-time fail safe). To validate the benefits of EnergyShield\, we implemented and tested it in the Carla simulation environment. Our results show that EnergyShield maintains safe vehicle operation while providing significant energy savings compared to on-vehicle NN evaluation: from 24% to 54% less energy across a range of wireless conditions and edge delays. \nBiography: \nOdema received a B.Sc degree in Electronics and Communications in 2014 and a M.Sc degree in Computer Engineering in 2018 from Ain Shams University\, Egypt. He is currently pursuing a Ph.D. degree in Computer Engineering at UCI where his current research interests are focused on HW/SW co-design methodologies for enhancing the performance efficiency of key AI workloads as from vision and NLP applications in emerging domains such as Edge-AI\, autonomous systems\, and tinyML.
URL:https://www.cecs.uci.edu/event/provably-safe-offloading-of-neural-network-controllers-for-energy-efficiency-in-autonomous-driving-systems/
LOCATION:EH 2430\, Engineering Hall\, University of California\, Irvine\, Irvine\, CA\, 92697\, United States
CATEGORIES:Student Seminars
ATTACH;FMTTYPE=image/jpeg:https://cecs.uci.edu/files/2024/05/odema.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20240126T140000
DTEND;TZID=America/Los_Angeles:20240126T150000
DTSTAMP:20240118T174157Z
CREATED:20240118T163958Z
LAST-MODIFIED:20240118T174157Z
UID:15949-1706277600-1706281200@www.cecs.uci.edu
SUMMARY:Modeling\, Analysis\, Simulation\, and Optimization. The Bedrock of Engineering
DESCRIPTION:Title: Modeling\, Analysis\, Simulation\, and Optimization. The Bedrock of Engineering \nSpeaker: Dr. Sani Nassif \nDate and Time: Friday\, January 26th\, 2:00 pm \nLocation: EH 2430 \nAbstract: \nVLSI\, Circuit Design\, Technology Scaling\, Moore’s Law\, EDA. They are our own highly specialized areas of expertise\, and it often feels like our discipline is quite different from other fields in engineering. Indeed\, the many decades of exponential growth are unique to our field and have presented numerous challenges that were met by researchers in this area with clever solutions. But at the core of our work\, we find four steps that we take over and over again. We observe phenomena\, make physical or empirical models for them\, analyze their behavior as it impacts our goals\, create mathematical models that we can use to simulate and predict the behaviors\, and finally apply optimization or improvement techniques to create the best possible outcome. These four activities are universal across engineering practice\, and it is useful to reflect on how our own tricks and techniques -many innovated in response to the severe scaling challenges the community has had to go through\, are good lessons to apply in other fields of engineering or even in medicine. \nBiography: \nSani received his PhD from Carnegie-Mellon university in the eighties. He worked for ten years at Bell Laboratories on various aspects of design and technology coupling. He then joined IBM Research where he was for eighteen years working on DFM in various technical and management roles. In 2014 he formed Radyalis to apply EDA techniques to Cancer Radiation Therapy. Sani is a fellow of the IEEE\, a member of the IBM Academy of Technology\, and an IBM master inventor with 70+ patents. He was the president of IEEE CEDA in 2014-2016\, and has published and presented widely. \nHosted By: Fadi Kurdahi \nMore Information
URL:https://www.cecs.uci.edu/event/modeling-analysis-simulation-and-optimization-the-bedrock-of-engineering/
LOCATION:EH 2430\, Engineering Hall\, University of California\, Irvine\, Irvine\, CA\, 92697\, United States
CATEGORIES:Seminars at CECS
ATTACH;FMTTYPE=image/png:https://cecs.uci.edu/files/2024/01/Sani-Nassif-picture.png
END:VEVENT
END:VCALENDAR