A key difficulty in the deployment of machine learning solutions remain their inherent fragility and difficulty of
certification. Formal verification has long been employed in the analysis and debugging of traditional computer systems, including hardware, but its deployment in the context of safety-critical AI-systems remains largely unexplored.
In this talk I will summarize some of the contributions on verification of neural systems from the Verification of Autonomous Systems Lab at Imperial College London, focusing on the issue of specification and verification for deep neural classifiers.
Schedule
Timezone: PDT
Verification of ML-based AI systems and its applicability in Edge ML
Alessio LOMUSCIO, Royal Academy of Engineering Chair in Emerging Technologies
Imperial College of London
A key difficulty in the deployment of machine learning solutions remain their inherent fragility and difficulty of
certification. Formal verification has long been employed in the analysis and debugging of traditional computer systems, including hardware, but its deployment in the context of safety-critical AI-systems remains largely unexplored.
In this talk I will summarize some of the contributions on verification of neural systems from the Verification of Autonomous Systems Lab at Imperial College London, focusing on the issue of specification and verification for deep neural classifiers.
Alessio LOMUSCIO, Royal Academy of Engineering Chair in Emerging Technologies
Imperial College of London
Schedule subject to change without notice.