PORTALE DELLA DIDATTICA

Ricerca CERCA
  KEYWORD

Microelectronics

Edge Performance Benchmarking for AI algorithms”

azienda 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




© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY
Contatti