BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.11//EN
BEGIN:VEVENT
UID:1036@edgeaihub.co.uk
DTSTART;TZID=Europe/London:20261124T140000
DTEND;TZID=Europe/London:20261124T150000
DTSTAMP:20261023T131516Z
URL:https://edgeaihub.co.uk/events/national-edge-ai-hub-webinar-series-tow
 ards-reliable-and-efficient-edge-ai-compression-and-certified-verification
 -of-neural-representations/
SUMMARY:National Edge AI Hub Webinar Series: Towards Reliable and Efficient
  Edge AI: Compression and Certified Verification of Neural Representations
DESCRIPTION:As artificial intelligence is increasingly deployed in resource
 -constrained environments\, ensuring systems are both efficient and trustw
 orthy is becoming a critical research challenge. In this webinar\, Dr Moha
 mmad Kazemi (Imperial College London) will explore recent advances in the 
 compression and certified verification of neural representations\, highlig
 hting how these techniques can support the development of reliable\, resou
 rce-efficient Edge AI systems.\n\nTitle:\n\nTowards Reliable and Efficient
  Edge AI: Compression and Certified Verification of Neural Representations
 \n\nSpeaker: Dr Mohammad Kazemi\, Imperial College London\nDate: November 
 24th\nTime: 2 PM GMT\n\nPlease register below to get invited to the webina
 r via Microsoft Teams. \n\nAbstract:\n\nDeploying artificial intelligence
  in resource-constrained environments requires addressing challenges beyon
 d predictive accuracy\, particularly computational efficiency\, memory req
 uirements\, and reliability. Implicit neural representations (INRs)\, whic
 h encode signals and continuous data through neural networks\, offer a fle
 xible and powerful approach to representing complex information. However\,
  making these representations compact and ensuring their reliable behaviou
 r remain important challenges.\n\nIn this webinar\, I will discuss recent 
 research on the compression and certified verification of implicit neural 
 representations\, focusing on our CertINR framework. I will introduce the 
 underlying mathematical ideas\, explain how compression and formal verific
 ation can be addressed\, and present the associated theoretical and experi
 mental findings. The talk will also explore the relevance of these techniq
 ues to trustworthy and resource-efficient Edge AI\, highlighting potential
  applications and open research directions.\n\nBio: Dr. Mohammad Kazemi is
  a Research Associate in Edge AI at the Department of Computing\, Imperial
  College London\, working with Professor Julie McCann in the Adaptive Emer
 gent Systems Engineering (AESE) group. Previously a Marie Skłodowska-Curi
 e Fellow at Imperial\, his research spans machine learning\, information 
 theory\, and wireless communications\, with an emphasis on developing effi
 cient and reliable intelligent systems. His current work includes neural r
 epresentation learning\, formal verification\, and task-oriented communica
 tion for distributed sensing applications.
CATEGORIES:Research Webinar
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/London
X-LIC-LOCATION:Europe/London
BEGIN:STANDARD
DTSTART:20261025T010000
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
END:STANDARD
END:VTIMEZONE
END:VCALENDAR