Indium–Gallium–Zinc Oxide-Based Synaptic Charge Trap Flash for Spiking Neural Network-Restricted Boltzmann Machine

Abstract

Recently, neuromorphic computing has been proposed to overcome the drawbacks of the current von Neumann computing architecture. Especially, spiking neural network (SNN) has received significant attention due to its ability to mimic the spike-driven behavior of biological neurons and synapses, potentially leading to low-power consumption and other advantages. In this work, we designed the indium–gallium–zinc oxide (IGZO) channel charge-trap flash (CTF) synaptic device based on a HfO2/Al2O3/Si3N4/Al2O3 layer. Our IGZO-based CTF device exhibits synaptic functions with 128 levels of synaptic weight states and spike-timing-dependent plasticity. The SNN–restricted Boltzmann machine was used to simulate the fabricated CTF device to evaluate the efficiency for the SNN system, achieving the high pattern-recognition accuracy of 83.9%. We believe that our results show the suitability of the fabricated IGZO CTF device as a synaptic device for neuromorphic computing.

Efficient Spiking Neural Networks with Biologically Similar Lithium-Ion Memristor Neurons

“…Spike neural networks (SNN), benefiting from the event-driven nature and the sparse asynchronous binary peaking coding, are considered as potential alternatives to ANNs for ultralow power consumption. − Neural models have been proposed for the SNN as McCulloch–Pitts (MP), , Hodgkin–Huxley (H–H), , integrate-and-fire (IF), − and leak-integrate-and-fire (LIF). − Among the models, the LIF model, a representative synaptic element, plays an important role in the construction of SNN systems because it can simultaneously deal with the spatial and temporal integration of input signals, continuously achieve the leakage and firing function, and even mimic the threshold dynamics of biological neurons. , Importantly, artificial synapses combined with peripheral circuits can build LIF models that replicate similar structures of biological neurons. , …”