WP1: Trustworthy Hybrid-AI
Develop an Hybrid AI intrinsically more regular
> More understandable, explainable, verifiable
with WP2,3,8 for Machine Learning
Interactive Explanations for developers
> Understand what is happening and raise alarms around potential problems.
with WP4,5 for human interaction
with WP6,7 for problems to look for (bias, privacy, legal aspects…)
Neuro-symbolic execution
Automatic Trust Enhancement
=> Tools to improve automatically the component / the system
Certification engine
> Provide guarantees about the behaviour of the component or the system.
Team members
Lead PI SG: Abhik ROYCHOUDHURY (NUS SoC)
Team PI Singapore
Brian LIM (NUS SoC)
Kuldeep MEEL (NUS SoC)
Reza SHOKRI (NUS SoC)
Lead PI FR: Blaise GENEST (CNRS)
Team PI France
Leila AMGOUD (CNRS)
Nicholas ASHER (CNRS)
Jean-Bernard LASSERRE (CNRS)
Joao MARQUES-SILVA (CNRS)
Abstract
The researchers in WP1 have an excellent track record in formal methods, artificial intelligence and trustworthy systems. This includes recipients of IEEE fellowships (Joao Marques Silva), winner of prestigious recent awards (Reza Shokri was winner of Casper Bowden award for outstanding research in Privacy Enhancing Technologies in 2018) and directorships of relevantefforts as well as chair professorships (Abhik Roychoudhury, Reza Shokri and Kuldeep Meel).
Synergies between France and Singapore teams:
The French team is specialized on assessing and quantifying the trustworthiness of a system, while the Singapore team brings strong assets in making a system more trustworthy.On the explainability front, the Singapore team brings the expertise to obtain pertinent explanations from AI components, while the French team brings the interactive methodology to generate explanations adapted to a particular user through the concept of argumentation and explanatory power.
More links
This research is supported by the National Research Foundation, Prime Minister’s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme.
CREATE is an international collaboratory housing research centres set up by top universities. At CREATE, researchers from diverse disciplines and backgrounds work closely together to perform cutting-edge research in strategic areas of interest, for translation into practical applications leading to positive economic and societal outcomes for Singapore. The interdisciplinary research centres at CREATE focus on four areas of interdisciplinary thematic areas of research, namely human systems, energy systems, environmental systems and urban systems. More information on the CREATE programme can be obtained from www.create.edu.sg.
Visit the CNRS website here.