Antonello Rosato
Assistant Professor, Ph.D.
Electrical Engineering (IIET-01/A)
Department of Information Engineering, Electronics and Telecommunications (DIET)
Sapienza University of Rome
Assistant Professor, Ph.D.
Electrical Engineering (IIET-01/A)
Department of Information Engineering, Electronics and Telecommunications (DIET)
Sapienza University of Rome
Antonello Rosato was born in 1990; he received the M.Sc. degree with honors in Communications Engineering in 2015 and the Ph.D. degree in Information and Communication Technologies in 2018, both from the University of Rome “La Sapienza”, Italy. He is currently an Assistant Professor (since 2022) at the Department of Information Engineering, Electronics and Telecommunications (DIET) of the same university, where he teaches courses on machine learning and quantum computing for the Master’s degrees in Electronics, Telecommunications, and Industrial/Management Engineering, as well as a Ph.D. course on hyperdimensional computing. From 2019 to 2022 he was a postdoctoral research fellow at DIET and at the Department of Astronautical, Electrical and Energy Engineering (DIAEE) of Sapienza; previously, he worked in industry on audio signal processing and machine learning.
His research concerns machine learning and computational intelligence, with a focus on distributed and federated learning, randomized and recurrent neural networks, hyperdimensional computing / vector symbolic architectures, and quantum machine learning. Applications include forecasting and energy management in smart grids and energy communities, structural health monitoring of space structures, and the analysis of biomedical signals.
He is Associate Editor of the IEEE Transactions on Neural Networks and Learning Systems, he is part of the Editorial Board Member of Energies (MDPI), and a founding member of the IEEE CIS Task Force on Hyperdimensional Computing. He has organized special sessions and workshops in multiple IEEE conferences.
He has long been active in the University’s third mission, combining science outreach with technology transfer, and bringing AI beyond the university both through outreach initiatives and through technology transfer as co-founder of the Sapienza start-up GRID+ S.r.l.
Neural, fuzzy-neural and deep models for predicting and analysing multivariate time series from physical systems, with particular attention to how the input sequence is represented. The main application is forecasting and management in energy systems, from photovoltaic plants to energy communities; the same models are used for vibration data from space structures and for physiological signals.
Learning when data and computation are spread across several agents, from decentralized clustering and consensus training to federated learning. Hyperdimensional computing and vector symbolic architectures entered this work as a way to compress and combine randomized neural networks, and are now studied in their own right: theory, new learning problems and hardware implementation.
Learning models designed for near-term quantum hardware: quantum and hybrid quantum-classical recurrent networks for sequence data, quantum reservoir models, variational optimization and knowledge distillation. The work started from a quantum version of a randomized neural network in 2019 and now includes connections between quantum circuits and hyperdimensional computing.
A shortlist of the most representative papers; for the full list go to Publications page.
A. Rosato, M. Panella, R. Araneo, and A. Andreotti, “A Neural Network Based Prediction System of Distributed Generation for the Management of Microgrids”, IEEE Transactions on Industry Applications, 2019. DOI: 10.1109/TIA.2019.2916758
A. Rosato, M. Panella, A. Andreotti, O.A. Mohammed, and R. Araneo, “Two-stage dynamic management in energy communities using a decision system based on elastic net regularization”, Applied Energy, 2021. DOI: 10.1016/j.apenergy.2021.116852
D. Kleyko, A. Rosato, E. Paxon Frady, M. Panella, and F.T. Sommer, “Perceptron Theory Can Predict the Accuracy of Neural Networks”, IEEE Transactions on Neural Networks and Learning Systems, 2024. DOI: 10.1109/TNNLS.2023.3237381
A. Ceschini, A. Rosato, and M. Panella, “Design of an LSTM Cell on a Quantum Hardware”, IEEE Transactions on Circuits and Systems II: Express Briefs, 2022. DOI: 10.1109/TCSII.2021.3126204
M. Angioli, A. Rosato, M. Barbirotta, R. Martino, F. Menichelli, and M. Olivieri, “HD-CB: The First Exploration of Hyperdimensional Computing for Contextual Bandits Problems”, IEEE Open Journal of the Computer Society, 2026. DOI: 10.1109/OJCS.2025.3642108