Energy-efficient machine learning models that can run directly on edge devices are of great interest in IoT applications, as they can reduce network pressure and response latency, and improve privacy. An effective way to obtain energy-efficiency with small accuracy drops is to sequentially execute a set of increasingly complex models, early-stopping the procedure for 'easy' inputs that can be confidently classified by the smallest models. As a stopping criterion, current methods employ a single threshold on the output probabilities produced by each model. In this work, we show that such a criterion is sub-optimal for datasets that include classes of different complexity, and we demonstrate a more general approach based on per-classes thresholds. With experiments on a low-power end-node, we show that our method can significantly reduce the energy consumption compared to the single-threshold approach.

Energy-efficient adaptive machine learning on IoT end-nodes with class-dependent confidence / Daghero, F.; Burrello, A.; Jahier Pagliari, D.; Benini, L.; Macii, E.; Poncino, M.. - ELETTRONICO. - (2020), pp. 1-4. (Intervento presentato al convegno 27th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2020 tenutosi a Virtual conference nel 2020) [10.1109/ICECS49266.2020.9294863].

Energy-efficient adaptive machine learning on IoT end-nodes with class-dependent confidence

Daghero F.;Burrello A.;Jahier Pagliari D.;Macii E.;Poncino M.
2020

Abstract

Energy-efficient machine learning models that can run directly on edge devices are of great interest in IoT applications, as they can reduce network pressure and response latency, and improve privacy. An effective way to obtain energy-efficiency with small accuracy drops is to sequentially execute a set of increasingly complex models, early-stopping the procedure for 'easy' inputs that can be confidently classified by the smallest models. As a stopping criterion, current methods employ a single threshold on the output probabilities produced by each model. In this work, we show that such a criterion is sub-optimal for datasets that include classes of different complexity, and we demonstrate a more general approach based on per-classes thresholds. With experiments on a low-power end-node, we show that our method can significantly reduce the energy consumption compared to the single-threshold approach.
2020
978-1-7281-6044-3
File in questo prodotto:
File Dimensione Formato  
Daghero et al. - 2020 - Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence.pdf

accesso riservato

Descrizione: Articolo principale (versione editoriale)
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.89 MB
Formato Adobe PDF
1.89 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
class_score_margin.pdf

accesso aperto

Descrizione: Articolo principale (post-print)
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 1.31 MB
Formato Adobe PDF
1.31 MB 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/11583/2909394