[PlanetKR] Spotlight Seminar on AI - Alessio Lomuscio - March 21, 2025

[Antonio LIETO]

[* Apologies in case of multiple posting *]

The Italian Association for Artificial Intelligence, in collaboration with
the AISB (Society for the Study of Artificial Intelligence and Simulation
of Behaviour, UK) is pleased to announce the next seminar of its Spotlight
Seminars on AI initiative:

March 21  – 5:00 P.M. (CET)

Title: Towards Verification of Neural Systems

Speaker: Alessio Lomuscio, Imperial College London, UK

Link Streaming: https://www.youtube.com/@AixiaIt/streams

Abstract:

A major challenge in deploying ML-based systems, such as ML-based computer
vision, is the inherent difficulty in ensuring their performance in the
operational design domain. The standard approach consists in extensively
testing models against a wide collection of inputs. However, testing is
inherently limited in coverage, and it is expensive in several domains.
Novel verification methods provide guarantees that a neural model meets its
specifications in dense neighbourhood of selected inputs. For example, by
using verification methods we can establish whether a model is robust with
respect to infinitely many re-illumination changes, or particular noise
patterns in the vicinity to an input. Verification methods can also be
tailored to specifications in the latent space and establish the robustness
of models against semantic perturbations not definable in the input space
(3D pose changes, background changes, etc). Additionally, verification
methods can be paired with learning to obtain robust learning methods
capable of generating models inherently more robust than those that may be
derived with standard methods. In this presentation I will succinctly cover
the key theoretical results leading to some of the present ML verification
technology, illustrate the resulting toolsets and capabilities, and
describe some of the use cases developed with our colleagues at Boeing
Research, including centerline distance estimation, object detection, and
runway detection. I will argue that verification and robust learning can be
used to obtain models that are inherently more robust than present learning
and testing approaches, thereby unlocking the deployment of applications in
society critical applications.




Bio: Alessio Lomuscio (http://www.doc.ic.ac.uk/~alessio) is Professor of
Safe Artificial Intelligence at Imperial College London (UK), where he
leads the Safe AI Lab (http://sail.doc.ic.ac.uk/). He is a Distinguished
ACM member, a Fellow of the European Association of Artificial Intelligence
and currently holds a Royal Academy of Engineering Chair in Emerging
Technologies. He is founding co-director of the UKRI Doctoral Training
Centre in Safe and Trusted Artificial Intelligence. Alessio's research
interests concern the development of verification methods for artificial
intelligence.  Since 2000 he has pioneered the development of formal
methods for the verification of autonomous systems and multi-agent systems,
both symbolic and ML-based. He has published over 200 papers in leading AI
and formal methods conferences and journals. He is the founder and CEO of
Safe Intelligence, a VC-backed Imperial College London spinout helping
users build and assure robust ML systems.

The joint AI*IA/AISB Committee of the Spotlight Seminars on AI,

Giuseppe De Giacomo

Floriana Grasso

Antonio Lieto

Bertie Muller

Luciano Serafini


-------------
Antonio Lieto, Ph.D
Associate Professor of Computer Science at the University of Salerno,
DISPC, Italy
Cognition Interaction and Intelligent Technologies Lab (CIIT Lab) @ Unisa
https://www.ciitlab.org
Research Associate at ICAR-CNR, Palermo, Italy
Home: https://www.antoniolieto.net
ACM Distinguished Speaker: https://speakers.acm.org/speakers/lieto_12489

Deputy Editor in Chief of JETAI (Journal of Exp. & Theor. Artif. Intell.,
T&F)
https://www.tandfonline.com/jetai
<https://www.tandfonline.com/action/journalInformation?show=editorialBoard&journalCode=teta20>

Associate Editor of Cognitive Systems Research (Elsevier)
https://www.journals.elsevier.com/cognitive-systems-research/editorial-board


Author of "Cognitive Design for Artificial Minds" (2021), Routledge, Taylor
& Francis.
https://www.amazon.com/dp/1138207950
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://kr.org/pipermail/planetkr/attachments/20250317/a4cfa9d4/attachment.htm>