General information
Organisation
The French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas :
• defence and security,
• nuclear energy (fission and fusion),
• technological research for industry,
• fundamental research in the physical sciences and life sciences.
Drawing on its widely acknowledged expertise, and thanks to its 16000 technicians, engineers, researchers and staff, the CEA actively participates in collaborative projects with a large number of academic and industrial partners.
The CEA is established in ten centers spread throughout France
Reference
SL-DRT-24-0606
Direction
DRT
Thesis topic details
Category
Technological challenges
Thesis topics
Low precision quantization of attention based neural network for embedded devices
Contract
Thèse
Job description
Deploying artificial intelligence (AI) represents a major challenge. Over the last years, AI has developed using increasingly large neural networks and massive data processing. Today, the challenge is to adapt these methods to run on small embedded components and as close as possible to industrial solutions. The research question adressed here is how to make neural networks as frugal as possible, so that they can be applied to embedded systems. This involves rethinking models to make them much more compact and efficient, using adapted topologies and compression methods, as well as coding information in a way that is suitable for inference on embedded targets.
More specifically, the candidate will be interested in neural networks based on the attention mechanism, such as Transformer networks. He will propose new compression methods adapted to these neural network models, based for example on quantization or distillation. The candidate will focus on the compatibility of the methods he proposes to make the networks embeddable on a hardware target. With this in mind, he will propose encodings adapted to hardware targets.
University / doctoral school
Ecole Doctorale Informatique et Mathématiques (InfoMaths)
INSA Lyon
Thesis topic location
Site
Saclay
Requester
Position start date
01/03/2024
Person to be contacted by the applicant
MOINEAU Cyril cyril.moineau@cea.fr
CEA
DRT/DSCIN/DSCIN/LIAE
Institut Carnot CEA List - CEA Saclay - Nano-INNOV
Bat 862 - PC 172 F-91191 Gif-Sur-Yvette Cedex
01 69 08 00 69
Tutor / Responsible thesis director
De DINECHIN Florent Florent.de-Dinechin@insa-lyon.fr
INSA Lyon
CITI Lab
CITI Laboratory
6 Av. des Arts 1st floor, 69100 Villeurbanne
+33 4 72 43 74 30
En savoir plus