Rosario Milazzo

Dottorando in Ingegneria Informatica E Dei Sistemi , 38^o ciclo (2022-2025)
Dipartimento di Automatica e Informatica (DAUIN)

Docente esterno e/o collaboratore didattico
Dipartimento di Automatica e Informatica (DAUIN)

rosario.milazzo@polito.it

Profilo

Dottorato di ricerca

Argomento di ricerca

Robust, accurate and efficient deep neural networks for satellite and mobility applications

Tutori

Presentazione della ricerca

Poster

Interessi di ricerca

Data science, Computer vision and AI

Biografia

Rosario Milazzo obtained his bachelor’s degree in Computer Engineering from Politecnico di Torino in 2020 and completed his master’s degree in 2022. After graduating, he joined the GRAINS research group in the Department of Control and Computer Engineering (DAUIN) at Politecnico di Torino as a scholarship holder. In February 2023, he was selected as a PhD candidate in Computer Engineering, funded by NODES (Nord Ovest Digitale e Sostenibile). His research primarily focuses on optimizing and enhancing the fault tolerance of neural networks for mobility and satellite applications. As computing platforms in vehicles and satellites become increasingly powerful, deploying deep learning applications in these domains is now feasible. However, this requires deep neural networks that maintain high accuracy, efficiency, and resilience even under transient faults, such as radiation-induced errors. His research aims to ensure that deep neural networks in these applications meet these requirements.

Didattica

Insegnamenti

Corso di laurea magistrale

Gestione dell'innovazione e sviluppo prodotto ICT. A.A. 2024/25, INGEGNERIA GESTIONALE. Collaboratore del corso
Gestione dell'innovazione e sviluppo prodotto ICT. A.A. 2023/24, INGEGNERIA GESTIONALE. Collaboratore del corso
Gestione dell'innovazione e sviluppo prodotto ICT. A.A. 2022/23, INGEGNERIA GESTIONALE. Collaboratore del corso

MostraNascondi A.A. passati

Ricerca

Gruppi di ricerca

GRAINS - GRAphics and INtelligent Systems (DAUIN)

Pubblicazioni

Pubblicazioni più recenti Vedi tutte le pubblicazioni su Porto@Iris

Milazzo, Rosario; Fosson, Sophie M.; Morra, Lia; Sterpone, Luca (2025)
Self-supervised pretraining and quantization for fault tolerant neural networks: friend or foe?. In: IEEE ACCESS, vol. 13, pp. 75546-75562. ISSN 2169-3536
Contributo su Rivista
Manigrasso, Francesco; Milazzo, Rosario; Russo, Alessandro; Lamberti, Fabrizio; Strand, ... (2025)
Mammography classification with multi-view deep learning techniques: investigating graph and transformer-based architectures. In: MEDICAL IMAGE ANALYSIS, vol. 99. ISSN 1361-8415
Contributo su Rivista
Milazzo, Rosario; De Marco, Vincenzo; De Sio, Corrado; Fosson, Sophie; Morra, Lia; ... (2024)
On the Fault Tolerance of Self-Supervised Training in Convolutional Neural Networks. In: 27th International Symposium on Design and Diagnostics of Electronic Circuits and Systems, Kielce (Polonia), 3-5 April 2024, pp. 110-115. ISBN: 979-8-3503-5934-3
Contributo in Atti di Convegno (Proceeding)
Bianco, Selene; Corcione, Valeria; Maragliano, Matteo; Chiara Rodi, Giovanna; Marangoni, ... (2024)
EASTERN project: Earth observation models for weather event mitigation. In: SPAICE Conference on AI in and for Space, London (UK), 17 – 19 September 2024, pp. 318-322
Contributo in Atti di Convegno (Proceeding)
Aicardi, Irene; Angeli, Stefano; Milazzo, Rosario; Lingua, Andrea Maria; Angela Musci, ... (2020)
A Python Customization of Metashape for Quasi Real-Time Photogrammetry in Precision Agriculture Application. In: R3 in Geomatics: Research, Results and Review / S.N., S.L., Springer, pp. 229-243. ISBN: 978-3-030-62799-7
Contributo in Volume

Società e imprese

Brevetti e altre proprietà intellettuali

Deep Neural Networks For Multi-View Mammography Classification. Brevetto nazionale
Inventori: Francesco Manigrasso Rosario Milazzo Lia Morra Alessandro Sebastian Russo