KEYWORD |
Edge Performance Benchmarking for AI algorithms”
Tesi esterna in azienda
Parole chiave MACHINE LEARNING, PATTERN RECOGNITION
Riferimenti LUCIANO LAVAGNO
Riferimenti esterni Marcello Babbi, Reply Torino
Gruppi di ricerca Microelectronics
Tipo tesi APPLIED RESEARCH
Descrizione In edge computing scenarios, AI solution are widely used to augment devices intelligence, and
they are the most demanding in terms of HW characteristics. The thesis project aims to quantify
an optimize the performances of the most common AI techniques considering different hardware
and software different optimization strategies on edge MCU platforms.
Conoscenze richieste Python programming, some knowledge of Machine Learning
Note The student will be involved in:
❑ SW requirements definition;
❑ Edge platform capability assessment and selection;
❑ AI algorithms (e.g. Deep Neural Network) development in different applications (e.g. Battery Diagnostic);
❑ On edge performance optimization and compression methods development (e.g. clustering and spiking);
❑ Write a complete software library to optimize algorithms deployment on MCU platforms.
❑ Architecture experimental testing for benchmarking.
Scadenza validita proposta 11/10/2024
PROPONI LA TUA CANDIDATURA