Professor Alessio Lomuscio, Imperial College London on "Towards verifying neural systems"

Conference TFNetworkAutumn21

Data Science - The beating heart of AI
➣ Conference overview and registration 
➣ YouTube TFNetworkSummer21 Conference Playlist 

Alessio Lomuscio, Professor of Safe Artificial Intelligence at the Department of Computing, Imperial College London, Royal Academy of Engineering Chair in Emerging Technologies, ACM Distinguished Member

He leads the Verification of Autonomous Systems Lab, developing methods and tools for the verification of AI systems so that they can be deployed safely and securely in applications of societal importance.

At present the team are contributing to the following research areas:

• Verification of neural systems and autonomous systems realised via machine-learning.
• Explainability and Fairness in AI systems.
• Parameterised verification of robotic swarms.
• Logic-based verification of multi-agent systems.

LinkedIn

Towards verifying neural systems

A key difficulty in the deployment of AI solutions, including machine learning, remains their inherent fragility and difficulty of certification and explainability. Formal verification has long been employed in the analysis and debugging of traditional computer systems, including hardware and networks, but its deployment in the context of AI-systems remains largely unexplored.