Fixed-point quantization and binarization are two reduction methods adopted to deploy Convolutional Neural Networks (CNN) on end-nodes powered by low-power micro-controller units (MCUs). While most of the existing works use them as stand-alone optimizations, this work aims at demonstrating there is margin for a joint cooperation that leads to inferential engines with lower latency and higher accuracy. Called CoopNet, the proposed heterogeneous model is conceived, implemented and tested on off-the-shelf MCUs with small on-chip memory and few computational resources. Experimental results conducted on three different CNNs using as test-bench the low-power RISC core of the Cortex-M family by ARM validate the CoopNet proposal by showing substantial improvements w.r.t. designs where quantization and binarization are applied separately.

CoopNet: Cooperative convolutional neural network for low-power MCUs / Mocerino, L.; Calimera, A.. - (2019), pp. 414-417. (Intervento presentato al convegno 26th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2019 tenutosi a ita nel 2019) [10.1109/ICECS46596.2019.8964993].

CoopNet: Cooperative convolutional neural network for low-power MCUs

Mocerino L.;Calimera A.
2019

Abstract

Fixed-point quantization and binarization are two reduction methods adopted to deploy Convolutional Neural Networks (CNN) on end-nodes powered by low-power micro-controller units (MCUs). While most of the existing works use them as stand-alone optimizations, this work aims at demonstrating there is margin for a joint cooperation that leads to inferential engines with lower latency and higher accuracy. Called CoopNet, the proposed heterogeneous model is conceived, implemented and tested on off-the-shelf MCUs with small on-chip memory and few computational resources. Experimental results conducted on three different CNNs using as test-bench the low-power RISC core of the Cortex-M family by ARM validate the CoopNet proposal by showing substantial improvements w.r.t. designs where quantization and binarization are applied separately.
2019
978-1-7281-0996-1
File in questo prodotto:
File Dimensione Formato  
08964993.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 667.33 kB
Formato Adobe PDF
667.33 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
main.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 370.98 kB
Formato Adobe PDF
370.98 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2819467