Alberto Dequino

Dottorando in Intelligenza Artificiale , 37^o ciclo (2021-2024)
Dipartimento di Automatica e Informatica (DAUIN)

On-device Learning and Inference Optimization for Lightweight Neural Networks and Transformers on Microcontrollers

Embedded systems

Green networking, sustainable networks, machine learning for networking,

Machine learning

Transformer

Ultra low power

Dequino, Alberto; Bompani, Luca; Benini, Luca; Conti, Francesco (2025)
Optimizing BFloat16 Deployment of Tiny Transformers on Ultra-Low Power Extreme Edge SoCs. In: JOURNAL OF LOW POWER ELECTRONICS AND APPLICATIONS, vol. 15. ISSN 2079-9268
Contributo su Rivista
Dequino, Alberto; Carpegna, Alessio; Nadalini, Davide; Savino, Alessandro; Benini, Luca; ... (2024)
Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks. In: 2024 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), Knoxville, TN (USA), 01-03 July 2024, pp. 240-245. ISBN: 979-8-3503-5411-9
Contributo in Atti di Convegno (Proceeding)
Dequino, A; Conti, Francesco; Benini, Luca (2022)
ViT-LR: Pushing the Envelope for Transformer-Based On-Device Embedded Continual Learning. In: 2022 IEEE 13th International Green and Sustainable Computing Conference (IGSC), Pittsburgh, PA (USA), 24-25 October 2022, pp. 1-6. ISBN: 978-1-6654-6550-2
Contributo in Atti di Convegno (Proceeding)
Burrello, Alessio; Dequino, Alberto; Jahier Pagliari, Daniele; Conti, Franceso; ... (2021)
TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference. In: 2021 IEEE/ACM International Symposium on Low Power Electronics and Design, ISLPED 2021, USA, 2021, pp. 1-6. ISBN: 978-1-6654-3922-0
Contributo in Atti di Convegno (Proceeding)