Design and Study of an Artificial Spiking Neuron Enabled by Low-Voltage SiOx-based ReRAM
Citations
Altmetric:
Alternative Title
Abstract
In this paper, we study the implementation of a SiO x ReRAM an artificial spiking neuron network (SNN) as a memristive synapse. The analog switching SiO x based resistive random access memory (ReRAM) uses room temperature process and switches at sub 1.2V, suitable for BEOL integration. We analyze the neuron circuit speed impact from ReRAM switching, supply voltage and power consumption. With an single industry I/O voltage of +1.8V besides necessary negative supply for bipolar signal generation, and by co-optimizing the neuron circuit in the region of μs, the operating speed can be 3 orders faster than existing reported SNN circuit. In addition, we show that the ReRAM switching time poses the speed bottleneck for the SNN circuit. In order to further enhance the SNN operating speed, improvement to the ReRAM switching time is needed, or the need to increase the voltage supply but at the expense of power consumption.
Keywords
Spiking Neural Network, Resistive Random Access Memory, Spike-Timing-Dependent Plasticity
Source Title
2019 IEEE SOI-3D-Subthreshold Microelectronics Technology Unified Conference (S3S)
Publisher
IEEE
Series/Report No.
Collections
Rights
CC0 1.0 Universal
Date
2021-01-20
DOI
10.1109/S3S46989.2019.9320502
Type
Article