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.
EnglishBinarization is an attractive strategy for implementing lightweight Deep Convolutional Neural Networks (CNNs). Despite the unquestionable savings offered, memory footprint above all, it may induce an excessive accuracy loss that prevents a widespread use. This work elaborates on this aspect introducing TentacleNet, a new template designed to improve the predictive performance of binarized CNNs via parallelization. Inspired by the ensemble learning theory, it consists of a compact topology that is end-to-end trainable and organized to minimize memory utilization. Experimental results collected over three realistic benchmarks show TentacleNet fills the gap left by classical binary models, ensuring substantial memory savings w.r.t. state-of-theart binary ensemble methods.
TentacleNet: A Pseudo-Ensemble Template for Accurate Binary Convolutional Neural Networks / Mocerino, Luca; Calimera, Andrea. - ELETTRONICO. - (2020), pp. 261-265. ((Intervento presentato al convegno IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) [10.1109/AICAS48895.2020.9073982].
| Titolo: | TentacleNet: A Pseudo-Ensemble Template for Accurate Binary Convolutional Neural Networks | |
| Autori: | ||
| Data di pubblicazione: | 2020 | |
| Abstract: | Binarization is an attractive strategy for implementing lightweight Deep Convolutional Neural Net...works (CNNs). Despite the unquestionable savings offered, memory footprint above all, it may induce an excessive accuracy loss that prevents a widespread use. This work elaborates on this aspect introducing TentacleNet, a new template designed to improve the predictive performance of binarized CNNs via parallelization. Inspired by the ensemble learning theory, it consists of a compact topology that is end-to-end trainable and organized to minimize memory utilization. Experimental results collected over three realistic benchmarks show TentacleNet fills the gap left by classical binary models, ensuring substantial memory savings w.r.t. state-of-theart binary ensemble methods. | |
| ISBN: | 978-1-7281-4922-6 | |
| Appare nelle tipologie: | 4.1 Contributo in Atti di convegno |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| 09073982.pdf | 2a Post-print versione editoriale / Version of Record | Non Pubblico - Accesso privato/ristretto | Administrator Richiedi una copia | |
| aicas20.pdf | 2. Post-print / Author's Accepted Manuscript | PUBBLICO - Tutti i diritti riservati | Visibile a tuttiVisualizza/Apri |
http://hdl.handle.net/11583/2819465
Copyright © 2021