-
Deep Learning-type methods. The focus will be on geodesic methods, the search for paths of minimum length according to an adapted metric, imposing for example a penalization of the curvature. In addition
-
FieldComputer scienceYears of Research ExperienceNone Research FieldMathematicsYears of Research ExperienceNone Additional Information Eligibility criteria PhD in computer science, deep learning, or data science
-
This position will consist of using "deep learning" methods, in particular CNNs and "transformers" for the processing of data from the IASI instrument from CNES. These observations are brightness temperature
-
, having a wide range of applications, from astronomical imaging to computational photography. In recent years, (deep) learning-based solutions have obtained state-of-the-art performance in many applications
-
- Statistical and programming skills (e.g., R, Python, Matlab, Praat scripting) - Strong interest in automatic speech processing and machine learning tools (e.g. deep speech processing, wav2vec...) - Prior
-
experiments and numerical simulations and will be divided into three parts: Microstructure: 1.1. Experimental Characterization: Using X-ray tomography, image analysis with conventional tools or deep learning
-
particular their detection using at least one of the above methods. - Languages and coding: python (essential), good background in Computer Sciences (expertise in AI/deep learning welcome). Values: enthusiasm