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].
Scheda prodotto non validato
I dati visualizzati non sono stati ancora sottoposti a validazione formale da parte dello Staff di IRIS, ma sono stati ugualmente trasmessi al Sito Docente Cineca (Loginmiur).
Titolo: | Impact of Layers Selective Approximation on CNNs Reliability and Performance | |
Autori: | Rech, R. L.; Rech, P. | |
Autori Unitn: | ||
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) |