On the distribution of clique-based neural networks for edge AI - Archive ouverte HAL Access content directly
Journal Articles IEEE Journal on Emerging and Selected Topics in Circuits and Systems Year : 2020

On the distribution of clique-based neural networks for edge AI

Abstract

Distributed smart sensors are more and more used in applications such as biomedical or domestic monitoring. However, each sensor broadcasts data wirelessly to the others or to an aggregator, which leads to energy-hungry sensor nodes not ensuring data privacy. To tackle both challenges, this work proposes to distribute the feature extraction and a part of a clique-based neural network (CBNN) in each sensor node. This scheme allows standardizing data at the sensor level, ensuring privacy if the data is intercepted. Besides, a lower number of bits is transmitted, thus limiting the communication overhead. The inherent redundancy of clique-based networks makes them resilient to out-of-range connections, allowing an additional power reduction in the sensor nodes. Compared with a localized CBNN in the aggregator, the distributed structure reduces the inference latency by 28%, the sensor energy consumption by 25% and increases the protocol robustness. The circuit implementation is possible with the use of single-cluster iterative clique-based circuits, and demonstrated for a posture recognition application. To this end, a hardware circuit has been fabricated and performs a classification using 115fJ per synaptic event per neuron in 83ns.
Fichier principal
Vignette du fichier
JETCAS _FINAL_VERSION_credits.pdf (1.24 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03321564 , version 1 (12-10-2021)

Identifiers

Cite

Benoit Larras, Antoine Frappé. On the distribution of clique-based neural networks for edge AI: [Invited]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2020, 10 (4), pp.469-477. ⟨10.1109/JETCAS.2020.3023481⟩. ⟨hal-03321564⟩
41 View
52 Download

Altmetric

Share

Gmail Facebook X LinkedIn More