Davide Piccinini

Dottorando in Ingegneria Elettrica, Elettronica E Delle Comunicazioni , 39o ciclo (2023-2026)
Dipartimento di Elettronica e Telecomunicazioni (DET)


Dottorato di ricerca

Argomento di ricerca

My work focuses on remote sensing applications and deployment of deep learning techniques.


Interessi di ricerca

Big Data, Machine Learning, Neural Networks and Data Science


I obtained my diploma in classical studies in 2017 having attended Liceo
Classico Vittorio Alfieri (90/100).
I graduated in Mathematics from the University of Turin in June 2020 after
completing a Bachelor’s Degree Program (102/110) and then I obtained a Master’s Degree in Mathematics from the University of Turin in
June 2023 (110/110 com laude and honors). My career plan was
focused on Differential Geometry and Analysis, with particular regard to Dif-
ferential Equations and Non-Linear Analysis.
My thesis work was a dissertation on rotating spirals in segregated reaction-
diffusion systems, which introduced me to the world of research. This research
topic highly revolved on differential equations and variational methods.
During the final year of my Master’s Program, I started to explore the vast
world of Machine Learning, with a particular emphasis on Deep Learning and
Neural Networks. Throughout the months I expanded my theoretical knowledge
of Neural Networks, their applications and the main architectures used, such as
Convolutional Neural, Residual Networks and Tranformers.
After few months of studying, I became determined to pursue a Ph.D. in Deep
Learning. I was and still am confident that I could usefully apply the knowledge,
the tools, the problem solving mentality and the abstract thinking I acquired
during my Bachelor’s and Master’s Degrees to many Machine Learning research
areas, such as Deep Learning. Moreover, I think that combining all the afore-
mentioned things I’ve learned from my studies in Mathematics with knowledge
in Computer Science and Machine Learning could help me offer a new perspec-
tive and a fresh approach to some Deep Learning problems and it might also
inspire me with interesting insights and ideas for research.
After the graduation I was offered the chance to start, in October 2023, a Re-
search Fellowship in Deep Learning at Politecnico di Torino with Prof. Enrico
Magli, an opportunity I was enthusiastic to accept.
The topics of the fellowship concerned building a
robust and efficient Edge-AI for remote Image Analysis, i.e. onboard a satellite,
and a new method for Quantization-Aware Training applied to Self-Supervised
environments, with particular regard to Self-Supervised Contrastive Learning.
After six moths, I was offered a P.h.D. scholarship with Prof. Enrico Magli wich I started in March 2024.
My research focuses on developing efficient deep learning techniques and models for remote sensing deployment,
with particular regard to possible on board usage.
Currently I am working on new models for analyze hyperspectral images, exploiting the new architectures that have been published in the
last few months.