Impact of Layers Selective Approximation on CNNs Reliability and Performance

In this paper, we evaluate the impact on reliability and performance of the selective approximation of Convolutional Neural Networks (CNNs) layers on NVIDIA mixed-precision architectures. We found that, even without affecting accuracy, the approximation from single to half precision of each layer has a different impact on both performance and output error.

Impact of Layers Selective Approximation on CNNs Reliability and Performance / Rech, R. L.; Rech, P.. - (2020), pp. 1-4. ((Intervento presentato al convegno 33rd IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2020 tenutosi a ita nel 2020 [10.1109/DFT50435.2020.9250821].

Titolo: Impact of Layers Selective Approximation on CNNs Reliability and Performance
Autori: Rech, R. L.; Rech, P.
Autori Unitn: 
Rech, Paolo
mostra contributor esterni 
Titolo del volume contenente il saggio: 33rd IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2020
Luogo di edizione: usa
Casa editrice: Institute of Electrical and Electronics Engineers Inc.
Anno di pubblicazione: 2020
Codice identificativo Scopus: 2-s2.0-85097647375
ISBN: 978-1-7281-9457-8
Handle: http://hdl.handle.net/11572/346645
Citazione: Impact of Layers Selective Approximation on CNNs Reliability and Performance / Rech, R. L.; Rech, P.. - (2020), pp. 1-4. ((Intervento presentato al convegno 33rd IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2020 tenutosi a ita nel 2020 [10.1109/DFT50435.2020.9250821].
Appare nelle tipologie:04.1 Saggio in atti di convegno (Paper in Proceedings)

File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
 
 
 
Powered by IRIS-about IRIS-Utilizzo dei cookie
Logo CINECA  Copyright © 2022