Lightweight AI inference on Embedded Systems
Parole chiave ARTIFICIAL INTELLIGENCE, FPGA
Riferimenti LUCA STERPONE
Gruppi di ricerca DAUIN - AEROSPACE AND SAFETY COMPUTING LAB
Tipo tesi RICERCA
Descrizione In recent years, the continuous development of artificial intelligence has largely been driven by algorithms, computing power and reliability. This thesis focuses on the design of inference methods of artificial intelligence implemented on programmable devices such as Field Programmable Gate Arrays. The design will focus on a lightweight model capable to address the issues of performance, cost, power consumption, flexibility, and robustness comprehensively. The thesis is performed in collaboration with the European Space Agency (ESA). It is planned a period as ESA intern during the framework of the thesis.
Conoscenze richieste Neural Networks, Computer Architecture
Scadenza validita proposta 01/04/2023 PROPONI LA TUA CANDIDATURA