Offre en lien avec l’Action/le Réseau : BigData4Astro/– — –

Laboratoire/Entreprise : LESIA, Observatoire de Paris-PSL
Durée : 18 to 24 months
Contact : baptiste.cecconi@obspm.fr
Date limite de publication : 2024-01-31

Contexte :
The EXTRACT project (EU, https://extract-project.eu) is currently conducting the design of an edge-to-cloud solution for heavy data processing based on Deep learning methodologies. One of the use case is the project Transient Astrophysics using SKA pathfinders (TASKA) that covers the processing of dynamical astronomical imaging data in radio using deep learning.

Radio astronomy imaging involves the inversion of set of Fourier domain samples acquired by an interferometer, observing a certain direction of the sky at a specific temporal and spectral rate.

The transformation from the recorded data (set of sparse and incomplete Fourier samples) to a multidimensional image cube containing scientific information, is a strong and ill-posed inverse problem.

For decades, « classical » radio interferometric imaging usually involved the production of single 2D image from the averaging (in time and frequency) of Fourier samples and solving the deconvolution problem to remove the instrumental impulse response. The target was to obtain a static image of the sky in radio. The classical CLEAN algorithm (1974) and CLEAN derivatives methods were historically the most widespread methods used to solve for the problem, mainly in the image space.

Sujet :
When the observed sky is steady, the accumulation of Fourier samples helps getting better images with improved signal-to-noise ratio (SNR) and image fidelity. However, if an astrophysical event (a.k.a. a radio « transient ») occurs during the observation, a long time integration can average out and prevent the detection of such short-lived event. Fast snapshot imaging using the same methods trying to follow fast variations of the sky provide a very limited SNR that would limit the detection level to only powerful astrophysical transients. In addition, extended time-variable emission (e.g., Solar flares, planetary emissions, etc.) are only poorly imaged using classical 2D imaging at a higher rate.

With the development of machine learning and deep learning (ML/DL) methodologies, solving for the imaging and deconvolution can be revisited to produce images cubes with the lowest possible bias while maintaining the integrity of the physical information measured from the sky. The imaging problem is analog to a video restoration problem where identified features are restored and tracked in time and spectral domains.

Hopefully, the astrophysical transients usually have a smooth behavior in time and spectral domains and can be located in a region of the sky. Therefore, the approach of this project is to model the varying source as a 4D structured signal that could be detected and restored with the appropriate approach of the data.

The developed networks will use trainings sets composed of simulated data as well as real data.

Profil du candidat :
(M/F) Post-Doc OR Research Engineer degree (>= 2 years experience in image processing)

Application domain: Applicant profile can come from various image processing and image restoration fields, such as medical imaging, astronomy, video restoration, industry, etc. Applications with a general scientific or signal processing background will be favoured.

Academic background: PhD or MsC degree in Computer Science or similar.

Formation et compétences requises :
We require candidates to have an moderate or advanced level of expertise in the following fields:
– Python/C++
– General knowledge in DL networks (e.g. CNN, GAN, Unet, mainly focused on image processing, image restoration or time series analysis etc.
– Knowledge of DL Frameworks (e.g. TensorFlow, keras, PyTorch
– (Optional) Inverse problem formulation and resolution
– (Optional) Fourier analysis and Fourier sampling
– (Optional) Data workflow management systems
– (Optional) Knowledge on edge/cloud technologies

Adresse d’emploi :
LESIA, Observatoire de Paris,
5 Place Jules Janssen,
92190 Meudon

Document attaché : 202312061248_Profil TASKA D-E-2.pdf

Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : LIRIS
Durée : 13 mois
Contact : hamida.seba@univ-lyon1.fr
Date limite de publication : 2024-01-31

Contexte :
A full-time 1 year postdoctoral position in Computer Science is available at the Laboratoire d’Informatique en Image et Systèmes d’information (LIRIS), Université Lyon 1 on Graph mining and learning

Sujet :
Research in graph mining and learning.
The position does not come with teaching duties, thus French is NOT mandatory.
Duration: 13 months
Staring: ASAP
Salary: according to experience (~2000-2500EUR of monthly net salary)
Location: Villeurbanne
There might be opportunities for the recruited candidate to supervise or co-supervise master students.

Applications include a detailed CV with a complete list of publications and should be sent to hamida.seba@univ-lyon1.fr

Profil du candidat :
* Completed PhD in Computer Science
* Strong academic background on graph algorithms and mining/learning methods.
* An interest on implementation aspects with Python/C++

Formation et compétences requises :
Phd in computer science

Adresse d’emploi :
Laboratoire d’Informatique en Image et Systèmes d’information (LIRIS), Université Lyon 1, Villeurbanne France

Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : Sorbonne Université
Durée : 12 moths
Contact : maria-victoria.eyharabide@sorbonne-universite.fr
Date limite de publication : 2024-01-31

Contexte :
1 Context

This research will be developed within the framework of the ANR BHAI project. The general aim of the project is to combine computer vision, NLP, knowledge engineering, and mathematical modeling of spatial relationships to help with the interpretation of Byzantine seals. This research aims to (i) fully recover the text on seals, (ii) work on the recognition of objects to analyze iconographic scenes, (iii) estimate the inception date of Byzantine seals, and (iv) propose solutions based on hybrid AI techniques to interpret damaged areas based on existing insights.

Sujet :
2 Information about the internship

• Project: ANR BHAI https://anr.fr/Project-ANR-21-CE38-0001
• Project’s members:
– Victoria Eyharabide, STIH Laboratory, Sorbonne Université (Project coordinator)
– Laurence Likforman-Sulem, Departement IDS, Telecom Paris
– Isabelle Bloch, LIP6 Laboratory, Sorbonne Université
– Beatrice Caseau, UMR 8167 Orient et Méditerranée, Sorbonne Université
• Location: Maison de la recherche, Sorbonne Université – 28 rue Serpente, 75006 Paris.
• Duration: 12 months
• Keywords: Deep Nets, Character recognition, NLP, Instance segmentation, Fuzzy Logic, Knowledge representation and reasoning, Byzantine sigillography.

Profil du candidat :
3 Profile of applicant

Applicants are required to have:
• A PhD in Computer Science.
• Advanced skills in Python programming are mandatory.
• A strong background in Machine Learning & Deep Learning on images and/or text using related libraries (scikitlearn, Tensorflow, Pytorch, etc.).

Formation et compétences requises :
• Fluency in written and spoken English is essential.
• Communication skills in French are a plus but not required.
• A good publication record will be a plus.

The position is open immediately. Review of applications will begin as soon as applications are received and continue until the position is filled.

Adresse d’emploi :
Maison de la recherche, Sorbonne Université
28 rue Serpente, 75006 Paris.

Document attaché : 202312051608_Postdoc_BHAI_2024.pdf

Offre en lien avec l’Action/le Réseau : – — –/Doctorants

Laboratoire/Entreprise : Université de Paris-Dauphine – PSL
Durée : 1 an renouvelable
Contact : bruno.chavesferreira@dauphine.fr
Date limite de publication : 2024-01-31

Contexte :
Créé au sein de l’Université Paris Sciences et Lettres (PSL) et hébergé à Paris Dauphine, l’Institut « Applied Computational Social Sciences » a pour vocation de renforcer la recherche sur les grandes problématiques sociétales (cohésion politique et sociale, transition écologique, transformation numérique, efficacité et compétitivité économique) en articulant sciences des données et sciences sociales.

L’Institut collecte et traite à larges échelle des données hétérogènes tant pour permettre des avancées scientifiques que pour contribuer à éclairer le débat public et la décision. Il réunit sur une équipe pluridisciplinaire de chercheurs et s’appuie sur une équipe d’ingénieurs qui apportent leurs expertises pour constituer des bases de données originales et opérer des traitements complexes. Ces projets sont initiés et portés par des laboratoires du CNRS, de Dauphine, de l’ENS, de l’INSP, et des MinesParis-Tech. Les résultats des travaux ont vocation à être largement diffusés auprès de partenaires institutionnels et du monde économique.

Sujet :
Dans le cadre du développement de l’Institut ACSS, l’Université PSL recrute une/un ingénieur(e) d’études (IE) en science des données. Elle/il sera chargé(e) de mettre en œuvre des méthodes et outils de collecte et traitement de données issues de sources variées (Web, bases de données institutionnelles, archives, etc.). Elle/il aura également la responsabilité de veiller au respect des bonnes pratiques en matière de développement et de gestion du code et des données. Enfin, ielle/il contribuera au développement de modèles statistiques ou d’apprentissage automatique (notamment dans le domaine du traitement automatisé de la langue naturelle).

Profil du candidat :
Formation :
Titulaire d’un master informatique, maths-info ou d’un diplôme d’école d’ingénieur.

Divers :
Peut convenir à un premier poste.
Il s’agit d’une création de poste sur CDD pour une durée de 1 an renouvelable
Rémunération suivant profil et expérience en fonction des grilles CNRS.
Le poste est basé à l’université de Paris Dauphine.

Formation et compétences requises :
Compétences nécessaires :
Connaissance approfondie de l’écosystème Python (et/ou R) en traitement, analyse et visualisation de données.
Maîtrise des bases de données relationnelles et NoSQL.
Méthodologies de développement : tests unitaires, gestion de versions (GIT).
Compréhension des méthodes scientifiques des sciences humaines et sociales.
Compétences additionnelles souhaitées :
Connaissance des paradigmes principaux d’apprentissage automatique (régression, classification supervisée, clustering, visualisation, etc.).
Pratique des services web modernes (architecture REST, formats JSON, XML, etc.) et des expressions régulières.
Une expérience en traitement de la langue naturelle (NLP) sera vivement appréciée.

Adresse d’emploi :
Université de Paris Dauphine
Pl. du Maréchal de Lattre de Tassigny, 75016 Paris

Document attaché : 202312051021_Ingenieur_IE_ACCS_2023_fr.pdf

Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : XLIM, university of Poitiers
Durée : 12 months
Contact : olfa.ben.ahmed@univ-poitiers.fr
Date limite de publication : 2024-01-31

Contexte :
We are looking for an outstanding and highly motivated Postdoctoral researcher in artificial intelligence, data science, or related fields to work on Meta-learning for low-prevalence disease detection. This postdoctoral position is part of the ANR JCJC MIMIC research project.

Sujet :
Context:

Deep learning-based approaches have seen an impressively good performance in the computer vision domain. However, huge, labeled datasets are needed to train on. Collecting such extensive annotated data is time and resource-consuming and it is not feasible for real-world applications, especially in the medical domain [1]. Developing deep learning approaches in the medical domain presents several challenges namely the scarcity and heterogeneity of data. In this position, the selected candidate will work on proposing data-efficient medical image analysis methods by addressing the current limitations of deep learning models in the medical domain.

Objectives:

This position aims to develop efficient deep-learning models using a small available medical imaging dataset for low-prevalence disease detection. We will investigate the recent development of meta-learning approaches [2] to facilitate quick adaptation of deep neural networks trained on data samples of common diseases for the identification of diseases with much less annotated data. Specifically, the selected candidate will focus on developing supervised meta-learning approaches taking into account the specificity of medical images. The work includes also leveraging the limited number of labeled images, along with potentially available unlabeled images to enhance the performance of the trained meta-learner.
The proposed methods will be tested and evaluated on medical diagnosis tasks representing real-world scenarios of low-prevalence disease detection, assessing the models’ ability to detect disease from small amounts of data.

Data used to implement different methods will be issued from our archives of imaging data collected in previous and current projects that involve Poitiers University Hospital. In addition, we will use several SOTA publicly available medical imaging datasets.
References :

[1] Chen, Xuxin, et al. “Recent advances and clinical applications of deep learning in medical image analysis.” Medical Image Analysis 79 (2022): 102444.
[2] Ouahab, Achraf, Olfa Ben-Ahmed, and Christine Fernandez-Maloigne. “A Self-attentive Meta-learning Approach for Image-Based Few-Shot Disease Detection.” MICCAI Workshop on Resource-Efficient Medical Image Analysis. Cham: Springer Nature Switzerland, 2022.

Profil du candidat :

• Ph.D. in Computer science and signal processing / Applied mathematics/ Artificial Intelligence, data sciences
• Strong skills in deep learning, mathematics, science, and data analysis…
• Programming experience in Python
• Experience in the medical imaging field would be a plus
• Experience in meta-learning will be a plus
• Excellent oral and written communication skills

Formation et compétences requises :
Salary :
Remuneration and social benefits are based on the collective wage agreement for public-sector employees at the national French level, considering previous years of experience. Salary between €2905 and €4081 gross monthly, depending on experience.

Start date and duration: The exact starting date is flexible and will be arranged with the candidate, and it should take place between February and April 2024. The position is funded for 12 months with a possible extension.

How to apply: Send your CV with a publications list, 2 names of references, and a motivation letter to olfa.ben.ahmed@univ-poitiers.fr

Adresse d’emploi :
Xlim site de Futuroscope, university of Poitiers