By continuing to browse the site, you are agreeing to our use of cookies. (More details)
Portal > Offres > Offre UMR7039-KONUSE-001 - Postdoc (12 mois) - méthodes tensorielles/apprentissage automatique (H/F)

Postdoc (12 months) - tensor methods/machine learning (M/F)

This offer is available in the following languages:
Français - Anglais

Ensure that your candidate profile is correct before applying. Your profile information will be added to the details for each application. In order to increase your visibility on our Careers Portal and allow employers to see your candidate profile, you can upload your CV to our CV library in one click!

Faites connaître cette offre !

General information

Reference : UMR7039-KONUSE-001
Date of publication : Friday, September 06, 2019
Type of Contract : FTC Scientist
Contract Period : 12 months
Expected date of employment : 1 December 2019
Proportion of work : Full time
Remuneration : between 2400 and 3000 € per month (before income tax), depending on experience
Desired level of education : PhD
Experience required : Indifferent


Remarkable results were recently achieved by deep neural networks architectures, in the context of many applied problems. Despite this success, they still have a number of drawbacks, including lack of interpretability and large number of parameters. In this project, we propose to simplify neural network architectures by allowing flexible nonlinear activation functions, contrary to fixed activation functions typically used. The proposed pathway is based on an original tensor-based technique for decomposition of multivariate maps.


The activities of the person to be hired include:
* development of tensor-based methods for learning and compression of neural network representations,
* development and implementation of algorithms, comparison with state-of-the-art methods,
* writing scientific articles and presenting the results at conferences
* participation in research meetings with project partners.


* PhD in signal processing, machine learning, applied mathematics, or a related discipline.
* Experience with tensor methods and/or neural networks/deep learning.
* Excellent programming skills; good command of MATLAB and/or Python.
* Fluency in English, written and oral; good communication skills.

Work Context

The postdoctoral position is open in the frame of the project LeaFleT (LEArning neural networks with FLExible nonlinearities by Tensor methods), coordinated by Konstantin Usevich (CNRS), and funded by Agence Nationale de la Recherche.

The successful candidate will be a part of the team SiMul (multidimensional signals) of CRAN (Centre de Recherche en Automatique de Nancy), a joint laboratory of CNRS and Université de Lorraine.

He/she will be primarily working with K. Usevich, S. Miron, and D. Brie. Other collaborators of the LeaFLeT project include researchers from LORIA (Nancy), GIPSA-lab (Grenoble), I2M (Marseille), and Vrije Universiteit Brussel (Belgium).

Additional Information

This is a 12-months contract, which can be renewed.

Please attach a CV, list of publications, 1-2 page research statement and contact details of two references, preferably in PDF.

We talk about it on Twitter!