Research Fellow in Machine Learning and or Formal Methods
DesCartes Program (Work Package 1) is looking for a Research Fellow in Machine Learning and or Formal Methods to develop explanability engines for AI systems, e.g. by generating meaningful explanations which can be adapted to suit the end-user.
The objective is to understand the behavior of the AI system wrt some hyperproperties (security, fairness, privacy…), focusing on using physics knowledge to improve the explanations.
DESCARTES PROGRAM
The DesCartes programme is developing a hybrid AI, combining Learning, Knowledge and Reasoning, which has good properties (need for less resources and data, security, robustness, fairness, respect for privacy, ethics), and demonstrated on industrial applications of the smart city (digital energy, monitoring of structures, air traffic control).
The program brings together 80 permanent researchers (half from France, half from Singapore), with the support of large industrial groups (Thales SG, EDF SG, ESI group, CETIM Matcor, ARIA etc.).
The research will take place mainly in Singapore, at the premises of CNRS@CREATE, with a competitive salary and generous funding for missions.
Read more about the DesCartes program here.
DESCRIPTION
In order to provide decision-making capabilities for next generation urban systems, we need to have confidence in the decisions taken by the AI systems.
One of DesCartes aim is to build core capabilities to establish and enhance confidence in the AI systems.
The higher assurance or confidence in AI technologies will come from explanability, and from formal verification and automated repair of AI systems to satisfy crucial hyper-properties such as robustness or fairness. Broader notion of a hybrid AI system will be developped with machine learning models co-operating with a software system and/or physical model, giving us greater flexibility in architecting technical solutions for verification and repair, that will be demonstrated on concrete cyber physical systems.
EXPERIENCE & QUALIFICATIONS
Minimum:
– PhD defended in Computer Science.
– Background and research experience in Formal Methods.
– Experience on programming environment.
Keywords:
- Research,
- Explanability,
- XAI
- Theoretical computer science,
- Logics in computer science,
- Algorithms,
- Human Computer Interface,
- Computer science,
- Artificial intelligence,
- Machine learning,
- CPS
FURTHER INFORMATION & CONTACT
Salary range: 6900-9000 (depending on suitability and experience)
Workplace Address: CREATE Tower (NUS Campus), 1 Create Way #08-01 Singapore 138602
Please send a short cover letter describing your suitability for the position, detailed CV with academic ranking (if any) and publication list, a concise description of research interests and future plans, and academic transcripts to:
Abhik Roychoudhury (Prof)
Blaise Genest (Prof)
We will begin reviewing applications for the positions immediately.