Matteo Grimaldi

Dottorato in Ingegneria Informatica E Dei Sistemi , 33^o ciclo (2017-2020)

Dottorato concluso nel 2021

Profilo

Argomento di ricerca

Hardware-aware compression techniques for Embedded Deep Neural Networks

Interessi di ricerca

Controls and system engineering

Life sciences

Biografia

Matteo Grimaldi received the M.Sc. degree in biomedical engineering from the Politecnico di Torino, in 2017. During the 2016-17 academic year, he joined the Motion Analysis Laboratory of the Department of Physical Medicine & Rehabilitation at Harvard Medical School, where he worked on the development and application of machine learning techniques in wearable technology. Since November 2017, he is pursuing the Ph.D. degree in control and computer engineering with the EDA group at Politecnico di Torino. His research interests include efficient algorithms and design strategies for resource-driven compression and optimization of deep learning models.

Premi e riconoscimenti

Dissemination activity (2021)
Fellow of the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) (2020)
Research Projects (2020)
2nd Best Paper Award 27th IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC) Cusco, October 6-9, 2019 (2020)

Didattica

Insegnamenti

Corso di laurea di 1° livello

Informatica. A.A. 2018/19, INGEGNERIA AEROSPAZIALE. Collaboratore del corso
Informatica. A.A. 2019/20, INGEGNERIA AEROSPAZIALE. Collaboratore del corso
Informatica. A.A. 2020/21, INGEGNERIA AEROSPAZIALE. Collaboratore del corso

MostraNascondi A.A. passati

Pubblicazioni

Pubblicazioni durante il dottorato Vedi tutte le pubblicazioni su Porto@Iris

Grimaldi, Matteo (2021)
Hardware-Aware Compression Techniques for Embedded Deep Neural Networks. relatore: MACII, Enrico; CALIMERA, ANDREA; , 33. XXXIII Ciclo, P.: 161
Doctoral Thesis
Grimaldi, Matteo; Peluso, Valentino; Calimera, Andrea (2020)
EAST: Encoding-Aware Sparse Training for Deep Memory Compression of ConvNets. In: IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), pp. 233-237. ISBN: 978-1-7281-4922-6
Contributo in Atti di Convegno (Proceeding)
Peluso, V.; Grimaldi, M.; Calimera, A. (2019)
Arbitrary-Precision Convolutional Neural Networks on Low-Power IoT Processors. In: 27th IFIP/IEEE International Conference on Very Large Scale Integration, VLSI-SoC 2019, per, 2019, pp. 142-147. ISBN: 978-1-7281-3915-9
Contributo in Atti di Convegno (Proceeding)
Grimaldi, Matteo; Peluso, Valentino; Calimera, Andrea (2019)
Optimality Assessment of Memory-Bounded ConvNets Deployed on Resource-Constrained RISC Cores. In: IEEE ACCESS, pp. 1-13. ISSN 2169-3536
Contributo su Rivista
Grimaldi, Matteo; Tenace, Valerio; Calimera, Andrea (2019)
Layer-wise compressive training for convolutional neural networks. In: FUTURE INTERNET, vol. 11. ISSN 1999-5903
Contributo su Rivista
Lee, Sunghoon I; Adans-Dester, Catherine P; Grimaldi, Matteo; Dowling, Ariel V; Horak, ... (2018)
Enabling Stroke Rehabilitation in Home and Community Settings: A Wearable Sensor-Based Approach for Upper-Limb Motor Training. In: IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE, vol. 6, pp. 2100411-11. ISSN 2168-2372
Contributo su Rivista

Mostra altre pubblicazioniMostra meno pubblicazioni