Located in Saclay, in southern Ile-de-France, CEA LIST is a scientific and technological research center dedicated to the development of software, embedded systems and sensors for applications intended for defense, security, energy, nuclear power, the environment and health. CEA LIST has more than 700 researchers focusing on intelligent digital systems, centered on artificial intelligence, the factory of the future, innovative instrumentation, cyberphysical systems and digital health.
Within this institute, the laboratories of the Digital Instrumentation Department work on the development and industrial transfer of cutting-edge technologies in AI, non-destructive control and nuclear instrumentation. The technical scope of our engineers and researchers concerns the analysis of signals (i.e. time series, but also spectra) produced by equipment developed internally, by CEA teams, or by external companies. The exploitation of this data is based on a broad spectrum of machine learning methods, relating to digital AI (deep neural networks, random forests, SVM) and symbolic AI (knowledge-based systems).
Mathématiques, information scientifique, logiciel
Post-doctorat
Post-doctoral fellowship in AI H/F
You will join a team made up of 6 permanent researchers, non-permanent researchers, doctoral students, interns and apprentices, united around the development of an AI called ExpressIF® (https://expressif.cea.fr).
18
ExpressIF® is a symbolic AI based on knowledge and reasoning, and of which we are also developing the ability to learn knowledge from data, text, images etc. ExpressIF® aims to be an alternative to deep neural networks and other current approaches (random forests, etc.) by offering our partners:
• Solving various problems: decision-making, optimal experimental plan design, planning, etc.
• Trusted AI whose models are understandable by humans and decisions are justifiable.
• An ethical AI which does not aim to replace the human experts but rather to dialogue with them to help them in their tasks.
• An AI capable of learning from little or a lot of data.
As part of a project which concerns the creation of innovative materials, we wish to strengthen our platform in its ability to learn from little experimental data.
In particular, we wish to work initially on the extraction of causal links between manufacturing parameters and property. Causality extraction is a subject of great importance in AI today and we wish to adapt existing approaches to experimental data and their particularities in order to select the variables of interest. Secondly, we will focus on these causal links and their characterization (causal inference) using an approach based on fuzzy rules, that is to say we will create fuzzy rules adapted to their representation.
Bibliography:
[1] Causal discovery for fuzzy rule learning. L Kunitomo-Jacquin, A Lomet, JP Poli. 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
[2] Towards monotonous functions approximation from few data with Gradual Generalized Modus Ponens: application to materials science. H Hajri, JP Poli, L Boudet. 2021 IEEE 33rd International Conference on Tools with Artificial Intelligence
[3] Towards an interpretable fuzzy approach to experimental design. O. Rousselle, J-P Poli, N. Ben Abdallah. IPMU 2024.
#CEA-List ; #PhD ; #Artificial Intelligence ; #AI
The candidate will have a doctorate in AI, statistics, applied mathematics or computer science.
The ability to work in a team is necessary, while demonstrating autonomy in daily tasks. As developments in AI advance rapidly, it is necessary for the candidate to have the ability to continually renew and enrich their skills. Finally, excellent expression skills, both oral and written, in English, will be necessary for you to communicate with our many partners. A taste for applied research is also important. Prototyping in python will be requested.
Saclay
France, Ile-de-France, Essonne (91)
Bac+8 - Doctorat scientifique
doctorate in AI, statistics, applied mathematics or computer science
Non
06/01/2025