All‐Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary Neurons

Abstract Artificial neurons and synapses are crucial for efficiently implementing spiking neural networks (SNNs) in hardware. The distinct functional requirements of artificial neurons and synapses present significant challenges in the implementation of area‐ and energy‐efficient SNNs. This study re...

Full description

Saved in:
Bibliographic Details
Main Authors: Jangsaeng Kim, Eun Chan Park, Wonjun Shin, Ryun‐Han Koo, Jiseong Im, Chang‐Hyeon Han, Jong‐Ho Lee, Daewoong Kwon
Format: Article
Language:English
Published: Wiley 2024-11-01
Series:Advanced Science
Subjects:
Online Access:https://doi.org/10.1002/advs.202407870
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846151474721062912
author Jangsaeng Kim
Eun Chan Park
Wonjun Shin
Ryun‐Han Koo
Jiseong Im
Chang‐Hyeon Han
Jong‐Ho Lee
Daewoong Kwon
author_facet Jangsaeng Kim
Eun Chan Park
Wonjun Shin
Ryun‐Han Koo
Jiseong Im
Chang‐Hyeon Han
Jong‐Ho Lee
Daewoong Kwon
author_sort Jangsaeng Kim
collection DOAJ
description Abstract Artificial neurons and synapses are crucial for efficiently implementing spiking neural networks (SNNs) in hardware. The distinct functional requirements of artificial neurons and synapses present significant challenges in the implementation of area‐ and energy‐efficient SNNs. This study reports an all‐ferroelectric SNN system through co‐optimization of material properties and device configurations using wafer‐scale atomic layer deposition. For the first time, a double‐gate (DG) morphotropic phase boundary‐based thin‐film transistor (MPBTFT) is utilized for a leaky integrate‐and‐fire (LIF) neuron. The DG MPBTFT‐based LIF neuron eliminates the need for capacitors and reset circuits, thereby enhancing area and energy efficiency. The DG configuration demonstrates various neuronal functions with high reliability. Co‐optimizing materials and devices significantly enhance the performance and functional versatility of artificial neurons and synapses. Meticulous material engineering facilitates the seamless co‐integration of DG MPBTFT‐based neurons, ferroelectric thin‐film transistor (TFT)–based synapses, and normal TFTs on a single wafer. All‐ferroelectric SNN systems achieved a high classification accuracy of 94.9%, thereby highlighting the potential of DG MPBTFT‐based LIF neurons for advanced neuromorphic computing.
format Article
id doaj-art-87be31e5dfb444b1941ab9b098b3838c
institution Kabale University
issn 2198-3844
language English
publishDate 2024-11-01
publisher Wiley
record_format Article
series Advanced Science
spelling doaj-art-87be31e5dfb444b1941ab9b098b3838c2024-11-27T11:21:53ZengWileyAdvanced Science2198-38442024-11-011144n/an/a10.1002/advs.202407870All‐Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary NeuronsJangsaeng Kim0Eun Chan Park1Wonjun Shin2Ryun‐Han Koo3Jiseong Im4Chang‐Hyeon Han5Jong‐Ho Lee6Daewoong Kwon7Department of Electronic Engineering Hanyang University Seoul 04763 Republic of KoreaDepartment of Electronic Engineering Hanyang University Seoul 04763 Republic of KoreaDepartment of Semiconductor Convergence Engineering Sungkyunkwan University Suwon 16419 Republic of KoreaDepartment of Electrical and Computer Engineering and Inter‐university Semiconductor Research Center Seoul National University Seoul 08826 Republic of KoreaDepartment of Electrical and Computer Engineering and Inter‐university Semiconductor Research Center Seoul National University Seoul 08826 Republic of KoreaDepartment of Electronic Engineering Hanyang University Seoul 04763 Republic of KoreaDepartment of Electrical and Computer Engineering and Inter‐university Semiconductor Research Center Seoul National University Seoul 08826 Republic of KoreaDepartment of Electronic Engineering Hanyang University Seoul 04763 Republic of KoreaAbstract Artificial neurons and synapses are crucial for efficiently implementing spiking neural networks (SNNs) in hardware. The distinct functional requirements of artificial neurons and synapses present significant challenges in the implementation of area‐ and energy‐efficient SNNs. This study reports an all‐ferroelectric SNN system through co‐optimization of material properties and device configurations using wafer‐scale atomic layer deposition. For the first time, a double‐gate (DG) morphotropic phase boundary‐based thin‐film transistor (MPBTFT) is utilized for a leaky integrate‐and‐fire (LIF) neuron. The DG MPBTFT‐based LIF neuron eliminates the need for capacitors and reset circuits, thereby enhancing area and energy efficiency. The DG configuration demonstrates various neuronal functions with high reliability. Co‐optimizing materials and devices significantly enhance the performance and functional versatility of artificial neurons and synapses. Meticulous material engineering facilitates the seamless co‐integration of DG MPBTFT‐based neurons, ferroelectric thin‐film transistor (TFT)–based synapses, and normal TFTs on a single wafer. All‐ferroelectric SNN systems achieved a high classification accuracy of 94.9%, thereby highlighting the potential of DG MPBTFT‐based LIF neurons for advanced neuromorphic computing.https://doi.org/10.1002/advs.202407870double‐gateleaky integrate‐and‐fire neuronmorphotropic phase boundaryneuromorphicspike‐frequency adaptationspiking neural networks
spellingShingle Jangsaeng Kim
Eun Chan Park
Wonjun Shin
Ryun‐Han Koo
Jiseong Im
Chang‐Hyeon Han
Jong‐Ho Lee
Daewoong Kwon
All‐Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary Neurons
Advanced Science
double‐gate
leaky integrate‐and‐fire neuron
morphotropic phase boundary
neuromorphic
spike‐frequency adaptation
spiking neural networks
title All‐Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary Neurons
title_full All‐Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary Neurons
title_fullStr All‐Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary Neurons
title_full_unstemmed All‐Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary Neurons
title_short All‐Ferroelectric Spiking Neural Networks via Morphotropic Phase Boundary Neurons
title_sort all ferroelectric spiking neural networks via morphotropic phase boundary neurons
topic double‐gate
leaky integrate‐and‐fire neuron
morphotropic phase boundary
neuromorphic
spike‐frequency adaptation
spiking neural networks
url https://doi.org/10.1002/advs.202407870
work_keys_str_mv AT jangsaengkim allferroelectricspikingneuralnetworksviamorphotropicphaseboundaryneurons
AT eunchanpark allferroelectricspikingneuralnetworksviamorphotropicphaseboundaryneurons
AT wonjunshin allferroelectricspikingneuralnetworksviamorphotropicphaseboundaryneurons
AT ryunhankoo allferroelectricspikingneuralnetworksviamorphotropicphaseboundaryneurons
AT jiseongim allferroelectricspikingneuralnetworksviamorphotropicphaseboundaryneurons
AT changhyeonhan allferroelectricspikingneuralnetworksviamorphotropicphaseboundaryneurons
AT jongholee allferroelectricspikingneuralnetworksviamorphotropicphaseboundaryneurons
AT daewoongkwon allferroelectricspikingneuralnetworksviamorphotropicphaseboundaryneurons