Sub-0.3V CMOS neuromorphic technology and its potential application

Francois Danneville (1) , Kevin Carpentier (2) , Ilias Sourikopoulos (3) , Michel Paindavoine (4) , Christophe Loyez (5, 6)

1 ANODE - IEMN - Advanced NanOmeter DEvices - IEMN
2 SATT NORD - Société d’Accélération du Transfert de Technologie
3 IEMN - Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520
4 LEAD - Laboratoire d'Etude de l'Apprentissage et du Développement [Dijon]
5 CSAM - IEMN - Circuits Systèmes Applications des Micro-ondes - IEMN
6 IRCICA - Institut de Recherche sur les Composants logiciels et matériels pour l'Information et la Communication Avancé - UAR 3380

The aim of this paper is to present a sub-0.3 V neuromorphic technology developed for spiking neural network design and its potential application. The main properties of the developed ultra low power (ULP) artificial neuron are first recalled. A description of ULP synapses follows that includes the plasticity scheme. The neuromorphic toolbox is then used to design a basic circuit allowing oriented edges classification. The circuit is made of 40 neurons and 108 plastic synapses, its consumed silicon core area is 0.025 mm 2 and the overall power consumption of 5 nW. Finally, the deployment of the technology within an industrial context to fabricate highly energy efficient Spike-based visual sensor is discussed.

Mots clés: ultra low power; artificial neuron and synapses; spiking neural networks; oriented edges; Spike-based visual sensor

Domaines: Micro et nanotechnologies/Microélectronique; Neurosciences [q-bio.NC]

Francois Danneville, Kevin Carpentier, Ilias Sourikopoulos, Michel Paindavoine, Christophe Loyez. Sub-0.3V CMOS neuromorphic technology and its potential application. 2021 International Conference on Content-Based Multimedia Indexing (CBMI 2021), Jun 2021, Lille, France. ⟨10.1109/CBMI50038.2021.9461899⟩. ⟨hal-03325599⟩