GARBAY Thomas

Dottore di ricerca
Gruppo di ricerca : SYEL
Data di partenza : 04/30/2023
https://lip6.fr/Thomas.Garbay

Relatore : Bertrand GRANADO

Co-relazione : HACHICHA Khalil

ZIP-CNN

Digital systems used for the Internet of Things (IoT) and Embedded Systems have seen an increasing use in recent decades. Embedded systems based on Microcontroller Unit (MCU) solve various problems by collecting a lot of data. Today, about 250 billion MCUs are in use. Projections in the coming years point to very strong growth.
Artificial intelligence has seen a resurgence of interest in 2012. The use of Convolutional Neural Networks (CNN) has helped to solve many problems in computer vision or natural language processing. The implementation of CNN within embedded systems would greatly improve the exploitation of the collected data. However, the inference cost of a CNN makes their implementation within embedded systems challenging.
This thesis focuses on exploring the solution space, in order to assist the implementation of CNN within embedded systems based on microcontrollers. For this purpose, the ZIP-CNN methodology is defined. It takes into account the embedded system and the CNN to be implemented. It provides an embedded designer with information regarding the impact of the CNN inference on the system. A designer can explore the impact of design choices, with the objective of respecting the constraints of the targeted application. A model is defined to quantitatively provide an estimation of the latency, the energy consumption and the memory space required to infer a CNN within an embedded target, whatever the topology of the CNN is. This model takes into account algorithmic reductions such as knowledge distillation, pruning or quantization. The implementation of state-of-the-art CNN within MCU verified the accuracy of the different estimations through a measurement process.

Difesa : 05/13/2023

Membri della commissione :

Fan Yang, Université de Bourgogne [Rapporteur]
Guy Gogniat, Université Bretagne Sud [Rapporteur]
Pierre Langlois, Polytechnique Montréal
Sébastien Pillement, Université de Nantes
Emanuelle Encrenaz, Sorbonne Université
Bertrand Granado, Sorbonne Université
Khalil Hachicha, Sorbonne Université
Andrea Pinna, Sorbonne Université
Wilfried Dron, ex Wisebatt - STMicroelectronics

Data di partenza : 04/30/2023

Pubblicazioni 2019-2023

Mentions légales
Mappa del sito