Dottorato in Ingegneria Elettrica, Elettronica E Delle Comunicazioni , 36^o ciclo (2020-2023)

Dottorato concluso nel 2024

Profilo

Argomento di ricerca

Optimized acceleration of deep neural networks on edge devices

Interessi di ricerca

Big Data, Machine Learning, Neural Networks and Data Science

VLSI theory, design and applications

Biografia

Emanuele Valpreda received the B.S. and M.S. (honors) degrees in electrical and electronics engineering from the Polytechnic University of Turin, in 2017 and 2019 respectively, where he is now pursuing the Ph.D. degree on energy efficient neural network acceleration for edge computing, under the supervision of Prof. Maurizio Martina. He worked from 2019 to 2022 with the Chair of Integrated Systems (LIS) at the Technical University of Munich (TUM), initially as a student and then as a guest researcher. His current research interests include neural network compression, reliability and approximate computing.

Didattica

Insegnamenti

Corso di laurea magistrale

Integrated systems architecture. A.A. 2021/22, INGEGNERIA ELETTRONICA (ELECTRONIC ENGINEERING). Collaboratore del corso
Integrated systems architecture. A.A. 2022/23, INGEGNERIA ELETTRONICA (ELECTRONIC ENGINEERING). Collaboratore del corso
Integrated systems architecture. A.A. 2023/24, INGEGNERIA ELETTRONICA (ELECTRONIC ENGINEERING). Collaboratore del corso
Digital Electronics. A.A. 2021/22, INGEGNERIA ELETTRONICA (ELECTRONIC ENGINEERING). Collaboratore del corso
Digital Electronics. A.A. 2022/23, INGEGNERIA ELETTRONICA (ELECTRONIC ENGINEERING). Collaboratore del corso
Digital Electronics. A.A. 2023/24, INGEGNERIA ELETTRONICA (ELECTRONIC ENGINEERING). Collaboratore del corso

MostraNascondi A.A. passati

Corso di laurea di 1° livello

Digital systems electronics. A.A. 2021/22, INGEGNERIA ELETTRONICA. Collaboratore del corso
Digital systems electronics. A.A. 2022/23, INGEGNERIA ELETTRONICA. Collaboratore del corso
Digital systems electronics. A.A. 2023/24, INGEGNERIA ELETTRONICA. Collaboratore del corso

MostraNascondi A.A. passati

Pubblicazioni

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

Guella, Flavia; Valpreda, Emanuele; Caon, Michele; Masera, Guido; Martina, Maurizio (2024)
TEMET: Truncated REconfigurable Multiplier with Error Tuning. In: International Conference on Applications in Electronics Pervading Industry, Environment and Society, Genova, Italy, 28-29 September 2023, pp. 370-377. ISSN 1876-1119. ISBN: 978-3-031-48121-5
Contributo in Atti di Convegno (Proceeding)
Dolmeta, Alessandra; Valpreda, Emanuele; Martina, Maurizio; Masera, Guido (2024)
Implementation and integration of NTT/INTT accelerator on RISC-V for CRYSTALS-Kyber. In: Proceedings of the 21st ACM International Conference on Computing Frontiers Workshops and Special Sessions, Ischia (Italy), May 7-9, 2024, pp. 59-62. ISBN: 9798400704925
Contributo in Atti di Convegno (Proceeding)
Guella, Flavia; Valpreda, Emanuele; Caon, Michele; Masera, Guido; Martina, Maurizio (2024)
MARLIN: A Co-Design Methodology for Approximate ReconfigurabLe Inference of Neural Networks at the Edge. In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS. I, REGULAR PAPERS, vol. 71. ISSN 1549-8328
Contributo su Rivista
Valpreda, Emanuele (2024)
Hardware/Neural Network Codesign for Energy-Efficient Inference on Edge Devices with Optimal Mapping and Compression. relatore: MARTINA, MAURIZIO; MASERA, Guido; , 36. XXXVI Ciclo, P.: 150
Doctoral Thesis
Valpreda, Emanuele; Palumbo, Giuseppe; Caon, Michele; Masera, Guido; Martina, Maurizio (2023)
ERODE: Error Resilient Object DetEction by Recovering Bounding Box and Class Information. In: 18th International Conference on PhD Research in Microelectronics and Electronics, Valencia (Spain), 18-21 June 2023, pp. 277-280. ISBN: 979-8-3503-0320-9
Contributo in Atti di Convegno (Proceeding)
Fasfous, Nael; Vemparala, Manoj Rohit; Frickenstein, Alexander; Valpreda, Emanuele; ... (2022)
AnaCoNGA: Analytical HW-CNN Co-Design Using Nested Genetic Algorithms. In: 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), Antwerp, Belgium, 14-23 March 2022, pp. 238-243. ISSN 1558-1101. ISBN: 978-3-9819263-6-1
Contributo in Atti di Convegno (Proceeding)
Fasfous, Nael; Frickenstein, Lukas; Neumeier, Michael; Vemparala, Manoj Rohit; ... (2022)
Mind the Scaling Factors: Resilience Analysis of Quantized Adversarially Robust CNNs. In: 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), Antwerp, Belgium, 14-23 March 2022, pp. 706-711. ISSN 1530-1591. ISBN: 978-3-9819263-6-1
Contributo in Atti di Convegno (Proceeding)
Rohit Vemparala, Manoj; Fasfous, Nael; Frickenstein, Alexander; Valpreda, Emanuele; ... (2022)
HW-Flow: A Multi-Abstraction Level HW-CNN Codesign Pruning Methodology. In: LEIBNIZ TRANSACTIONS ON EMBEDDED SYSTEMS, vol. 8, pp. 1-30. ISSN 2199-2002
Contributo su Rivista
Valpreda, Emanuele; Mori, Pierpaolo; Fasfous, Nael; Vemparala, Manoj Rohit; ... (2022)
HW-Flow-Fusion: Inter-Layer Scheduling for Convolutional Neural Network Accelerators with Dataflow Architectures. In: ELECTRONICS, vol. 11. ISSN 2079-9292
Contributo su Rivista
Aiello, Giuseppe; Bussolino, Beatrice; Valpreda, Emanuele; Ruo Roch, Massimo; Masera, ... (2022)
NLCMAP: A Framework for the Efficient Mapping of Non-Linear Convolutional Neural Networks on FPGA Accelerators. In: International Conference on Image Processing, Bordeaux, France, 16-19 October 2022. ISBN: 978-1-6654-9620-9
Contributo in Atti di Convegno (Proceeding)
Fasfous, Nael; Vemparala, Manoj Rohit; Frickenstein, Alexander; Valpreda, Emanuele; ... (2021)
HW-FlowQ: A Multi-Abstraction Level HW-CNN Co-design Quantization Methodology. In: ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, vol. 20, pp. 1-25. ISSN 1539-9087
Contributo su Rivista

Mostra altre pubblicazioniMostra meno pubblicazioni

Emanuele Valpreda

Dottorato in Ingegneria Elettrica, Elettronica E Delle Comunicazioni , 36o ciclo (2020-2023)

Tesi:

Tutori:

Presentazione della ricerca: