en
State University (France), Browse similar opportunities
SL-DRT-21-0446
Artificial intelligence & Data intelligence
Training and quantization of large-scale deep neural networks for transfer learningTransfer learning is today a common technique in Deep Learning that uses the learned parameters of a generic network (a feature extractor) to accelerate the training of another network on a more specific task. This specialized network is subsequently optimized for the hardware constraints of the specific use-case. However, given that the representations of the feature extractor are often rather generic, it might be possible to optimize the parameters before the transfer, to avoid that each end-user has to perform this optimization by herself. In this context, the thesis has the following scientific objectives:- Using several “unsupervised” learning methods (self-supervised, weakly supervised, semi-supervised) to train feature extractors on large datasets- Studying how common optimization methods (in particular quantization) can be applied on these extractors in a “task-agnostic” fashion- Quantifying the influence of these optimizations on the transfer learning capacity, by benchmarking and theoretical analysis (e.g. information compression theory)Required competences: Master degree (or equivalent), machine learning (in particular Deep Learning), programming (Python, Pytorch, Tensorflow, C++), good English (French knowledge is not required, but helpful)
Département Systèmes et Circuits Intégrés Numériques
Laboratoire Intelligence Artificielle Embarquée
Saclay
THIELE Johannes
CEA
DRT/DSCIN/DSCIN/LIAE
CEA SACLAY - NANO INNOVBAT. 86291191 GIF SUR YVETTE
Phone number: 33.1.69.08.25.10
Email: johannes.thiele@cea.fr
Paris-Saclay
Sciences et Technologies de l’Information et de la Communication (STIC)
Start date on
DELEZOIDE Bertrand
CEA
DRT/DIASI//LASTI
CEA SACLAY - NANO INNOVBAT. 861Point courier 17391191 GIF SUR YVETTE
Phone number: 33.1.69.08.01.53
Email: bertrand.delezoide@cea.fr
Choose the country you wish to travel to study for free, work or volunteer