PORTO @ 
Archivio Istituzionale della Ricerca
IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.
EnglishReconfigurable architectures targeting neural networks are an attractive option. They allow multiple neural networks of different types to be hosted on the same hardware, in parallel or sequence. Reconfigurability also grants the ability to morph into different micro-architectures to meet varying power-performance constraints. In this context, the need for a reconfigurable non-linear computational unit has not been widely researched. In this work, we present a formal and comprehensive method to select the optimal fixed-point representation to achieve the highest accuracy against the floating-point implementation benchmark. We also present a novel design of an optimised reconfigurable arithmetic unit for calculating non-linear functions. The unit can be dynamically configured to calculate the sigmoid, hyperbolic tangent, and exponential function using the same underlying hardware. We compare our work with the state-of-the-art and show that our unit can calculate all three functions without loss of accuracy.
NACU: A Non-Linear Arithmetic Unit for Neural Networks / Baccelli, Guido; Stathis, Dimitrios; Hemani, Ahmed; Martina, Maurizio. - ELETTRONICO. - 1(2020), pp. 1-6. ((Intervento presentato al convegno Design Automation Conference tenutosi a San Francisco (USA) nel 20-24 July 2020 [10.1109/DAC18072.2020.9218549].
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo
| Titolo: | NACU: A Non-Linear Arithmetic Unit for Neural Networks | |
| Autori: | ||
| Data di pubblicazione: | 2020 | |
| Abstract: | Reconfigurable architectures targeting neural networks are an attractive option. They allow multi...ple neural networks of different types to be hosted on the same hardware, in parallel or sequence. Reconfigurability also grants the ability to morph into different micro-architectures to meet varying power-performance constraints. In this context, the need for a reconfigurable non-linear computational unit has not been widely researched. In this work, we present a formal and comprehensive method to select the optimal fixed-point representation to achieve the highest accuracy against the floating-point implementation benchmark. We also present a novel design of an optimised reconfigurable arithmetic unit for calculating non-linear functions. The unit can be dynamically configured to calculate the sigmoid, hyperbolic tangent, and exponential function using the same underlying hardware. We compare our work with the state-of-the-art and show that our unit can calculate all three functions without loss of accuracy. | |
| ISBN: | 978-1-7281-1085-1 | |
| Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| 09218549.pdf | Versione editoriale | 2a Post-print versione editoriale / Version of Record | Non Pubblico - Accesso privato/ristretto | Administrator Richiedi una copia |
| NACU.pdf | Versione autore | 2. Post-print / Author's Accepted Manuscript | PUBBLICO - Tutti i diritti riservati | Visibile a tuttiVisualizza/Apri |
http://hdl.handle.net/11583/2848336
Copyright © 2021