BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal//recurring_events_ical//2.0//EN
BEGIN:VEVENT
UID:604b4499-603c-47df-8abb-df1eeefedb0c@www.nsf.gov
DTSTAMP:20250507T112007Z
DTSTART:20250626T150000Z
DTEND:20250626T161500Z
SUMMARY:Neurosymbolic Systems for Trustworthy AI
CONTACT:TeMari L Brown tlbrown@nsf.gov (703) 292-4688
DESCRIPTION:We invite you to our exciting upcoming CISE Distinguished Lectu
 re featuring Rajeev Alur, the esteemed Zisman Family Professor of Computer
  and Information Science and Founding Director of the ASSET Center for Tru
 stworthy AI at the University of Pennsylvania. Don’t miss it!Bio: Rajee
 v Alur is Zisman Family Professor of Computer and Information Science and 
 the Founding Director of ASSET Center for Trustworthy AI at University of 
 Pennsylvania. He obtained his bachelor's degree from IIT Kanpur and PhD fr
 om Stanford University. Before joining Penn, he was with Computing Science
  Research Center at Bell Labs. His research is focused on principles and t
 ools for design and analysis of safe and trustworthy systems. Notable awar
 ds include the inaugural CAV (Computer-Aided Verification) award, the inau
 gural Alonzo Church award, IIT Kanpur Distinguished Alumnus Award, and the
  Knuth Prize. He is the author of the textbook Principles of Cyber-Physica
 l Systems (MIT Press), has served as the chair of ACM SIGBED (Special Inte
 rest Group on Embedded Systems), was the lead PI of the NSF Expeditions in
  Computing project ExCAPE on program synthesis, and is the General Chair f
 or the upcoming Federated Logic Conference (FLoC).Abstract:Recent advances
  in deep learning have led to novel AI-based solutions to challenging comp
 utational problems. Yet, the state-of-the-art models do not provide reliab
 le explanations of how they make decisions, and can make occasional mistak
 es on even simple problems. The resulting lack of trust and reliability ar
 e obstacles to their adoption in safety-critical applications. Neurosymbol
 ic learning architectures aim to address this challenge by bridging the co
 mplementary worlds of deep learning and logical reasoning via explicit sym
 bolic representations. In this talk, I will describe representative neuros
 ymbolic systems, and how they enable more accurate, interpretable, and dom
 ain-aware solutions to problems in healthcare and robotics.Zoom Informatio
 nTopic: Neurosymbolic Systems for Trustworthy AIRegister in advance for th
 is webinar:https://nsf.zoomgov.com/webinar/register/WN_wQN47K3fT0ab4DchYhh
 L6QAfter registering, you will receive a confirmation email containing inf
 ormation about joining the webinar.\n  \n\n    \n\n\n\n                   
  June 26th, 2025: CISE Distinguished Lecture : Neurosymbolic Systems for T
 rustworthy AI \n            \n\n\n\n  \n    \n                \n  \n    \n
 \n\n\n\n    \n  Credit: U.S. National Science Foundation\n\n\n  Recent adv
 ances in deep learning have led to novel AI-based solutions to challenging
  computational problems. Yet, the state-of-the-art models do not provide r
 eliable explanations of how they make decisions, and can make occasional m
 istakes on even simple problems. The resulting lack of trust and reliabili
 ty are obstacles to their adoption in safety-critical applications. Neuros
 ymbolic learning architectures aim to address this challenge by bridging t
 he complementary worlds of deep learning and logical reasoning via explici
 t symbolic representations. In this talk, I will describe representative n
 eurosymbolic systems, and how they enable more accurate, interpretable, an
 d domain-aware solutions to problems in healthcare and robotics.\n\n 
LOCATION:Zoom Webinar
URL:https://www.nsf.gov/events/neurosymbolic-systems-trustworthy-ai/2025-06
 -26
END:VEVENT
END:VCALENDAR