I'm currently in the first year of a CIFRE thesis with the CHIPS team and Pellenc Selective Technologies (PellencST), based in Pertuis. Pellenc ST is a French company that designs, produces and markets intelligent, connected sorting equipment and services for the recycling industry.
My thesis focuses on the reduction of annotated data by applying design of experiments and active learning approaches. The aim is to minimise the need for manual annotation while optimising the performance of machine learning models. The aim of this research is to develop more efficient and economical methods for processing data, contributing to energy and annotation cost savings.
Deep active learning combined with design of experiments for waste sorting". The aim of this thesis is to reduce the number of annotations required to train a predictive model in the context of waste sorting by combining design of experiments and active learning approaches.
IMBE – UMR CNRS 7263 / IRD 237 / Aix Marseille Université / Avignon Université.
IMBE, Faculté des Sciences et Techniques St-Jérôme – Service 421 – Av. Escadrille Normandie Niémen
F-13 397 Marseille, cedex 20 – France
Téléphone : +33 (0)4 13 94 49 28
IMBE © 2024 - Production PYMAC, l’agence qui vous parle