Carbon-based Spiking Neural Network Implemented with Single-Electron Transistor and Memristor for Visual Perception

Spiking neural network (SNN) with synapses of memristor implemented for networking of neuromorphic devices, regarded as the most biologically interpretable neural network model, has shown great potential in emulating the information processing mechanism of brain-like computing. Carbon nanotube, full...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Zhiwei, Liu, Chenxi, Deng, Yabin, Huang, Zenan, He, Shan, Guo, Donghui
Format: Conference Proceeding
Language:English
Subjects:
carbon nanotube (CNT)
Germanium
graphene quantum dot (GQD)
Hafnium
memristor
Quality function deployment
single-electron transistor (SET)
spiking neural network (SNN)
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Spiking neural network (SNN) with synapses of memristor implemented for networking of neuromorphic devices, regarded as the most biologically interpretable neural network model, has shown great potential in emulating the information processing mechanism of brain-like computing. Carbon nanotube, fullerene nanoparticle and graphene quantum dot had been developed respectively for superconducting transmission line, single-electron transistor (SET) and non-volatile memory, artificial neural network with high density and low power consumption are becoming possible to be implemented with neuromorphic devices as well memristors via carbon-based nanoscale devices. In this paper, Coulomb oscillation of SETs is demonstrated as neuron spike firing, and the synaptic plasticity of memristor is characterized with graphene quantum dots of non-volatile properties as the SET's circuit, and the carbon-based SNN is proposed for visual perception.
ISSN:2163-5056
DOI:10.1109/ASID50160.2020.9271721