Enhanced Reliability and Self‐Compliance of Synaptic Arrays for Multibit Encoded Neuromorphic Systems

Abstract Utilizing memristors to increase the density of crossbar arrays requires reducing dependency on transistors. This paper presents an approach where the current limiting function is integrated within the memristor by inducing an AlOx/TaOx layer, thereby limiting overshoot current during filam...

Full description

Saved in:
Bibliographic Details
Main Authors: Sungjoon Kim, Hyeonseung Ji, Sungjun Kim, Woo Young Choi
Format: Article
Language:English
Published: Wiley-VCH 2025-02-01
Series:Advanced Electronic Materials
Subjects:
Online Access:https://doi.org/10.1002/aelm.202400282
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327596537380864
author Sungjoon Kim
Hyeonseung Ji
Sungjun Kim
Woo Young Choi
author_facet Sungjoon Kim
Hyeonseung Ji
Sungjun Kim
Woo Young Choi
author_sort Sungjoon Kim
collection DOAJ
description Abstract Utilizing memristors to increase the density of crossbar arrays requires reducing dependency on transistors. This paper presents an approach where the current limiting function is integrated within the memristor by inducing an AlOx/TaOx layer, thereby limiting overshoot current during filament formation. The reaction between TaOx and Al can be accelerated through annealing, which optimizes the on/off ratio and reduces device‐to‐device variation. Additionally, AlN is inserted to inhibit the movement of oxygen ions to the bottom electrode, improving conductive filament reoxidation. Furthermore, biological synaptic properties are examined using electrical pulse schemes, revealing multibit characteristics of >5‐bit. After the structure optimization, 24 × 24 crossbar arrays are fabricated, allowing 100% of cells to achieve self‐compliance filament formation without hard breakdown. Moreover, the crossbar array demonstrates an on/off ratio of over 4 × 102. Additionally, a multibit‐encoded neuromorphic system is proposed based on the device's multibit capability. The number of synapses can be significantly reduced by grouping input data into a single memristor device. When comparing classification accuracies, 97.14% and 95.54% are observed without and with encoding. The improvements in device structure and encoding method presented in this study enable highly integrated crossbar arrays and efficient neuromorphic systems.
format Article
id doaj-art-e7f0831eacd445e1b3cb3e763f5a45d3
institution Kabale University
issn 2199-160X
language English
publishDate 2025-02-01
publisher Wiley-VCH
record_format Article
series Advanced Electronic Materials
spelling doaj-art-e7f0831eacd445e1b3cb3e763f5a45d32025-08-20T03:47:49ZengWiley-VCHAdvanced Electronic Materials2199-160X2025-02-01112n/an/a10.1002/aelm.202400282Enhanced Reliability and Self‐Compliance of Synaptic Arrays for Multibit Encoded Neuromorphic SystemsSungjoon Kim0Hyeonseung Ji1Sungjun Kim2Woo Young Choi3Department of AI Semiconductor Engineering Korea University Sejong 30019 Republic of KoreaDivision of Electronics and Electrical Engineering Dongguk University Seoul 04620 Republic of KoreaDivision of Electronics and Electrical Engineering Dongguk University Seoul 04620 Republic of KoreaDepartment of Electrical and Computer Engineering and Inter‐university Semiconductor Research Center (ISRC) Seoul National University Seoul 08826 Republic of KoreaAbstract Utilizing memristors to increase the density of crossbar arrays requires reducing dependency on transistors. This paper presents an approach where the current limiting function is integrated within the memristor by inducing an AlOx/TaOx layer, thereby limiting overshoot current during filament formation. The reaction between TaOx and Al can be accelerated through annealing, which optimizes the on/off ratio and reduces device‐to‐device variation. Additionally, AlN is inserted to inhibit the movement of oxygen ions to the bottom electrode, improving conductive filament reoxidation. Furthermore, biological synaptic properties are examined using electrical pulse schemes, revealing multibit characteristics of >5‐bit. After the structure optimization, 24 × 24 crossbar arrays are fabricated, allowing 100% of cells to achieve self‐compliance filament formation without hard breakdown. Moreover, the crossbar array demonstrates an on/off ratio of over 4 × 102. Additionally, a multibit‐encoded neuromorphic system is proposed based on the device's multibit capability. The number of synapses can be significantly reduced by grouping input data into a single memristor device. When comparing classification accuracies, 97.14% and 95.54% are observed without and with encoding. The improvements in device structure and encoding method presented in this study enable highly integrated crossbar arrays and efficient neuromorphic systems.https://doi.org/10.1002/aelm.202400282crossbar arrayneuromorphic systemovershoot suppressed layerresistive switchingself‐compliance
spellingShingle Sungjoon Kim
Hyeonseung Ji
Sungjun Kim
Woo Young Choi
Enhanced Reliability and Self‐Compliance of Synaptic Arrays for Multibit Encoded Neuromorphic Systems
Advanced Electronic Materials
crossbar array
neuromorphic system
overshoot suppressed layer
resistive switching
self‐compliance
title Enhanced Reliability and Self‐Compliance of Synaptic Arrays for Multibit Encoded Neuromorphic Systems
title_full Enhanced Reliability and Self‐Compliance of Synaptic Arrays for Multibit Encoded Neuromorphic Systems
title_fullStr Enhanced Reliability and Self‐Compliance of Synaptic Arrays for Multibit Encoded Neuromorphic Systems
title_full_unstemmed Enhanced Reliability and Self‐Compliance of Synaptic Arrays for Multibit Encoded Neuromorphic Systems
title_short Enhanced Reliability and Self‐Compliance of Synaptic Arrays for Multibit Encoded Neuromorphic Systems
title_sort enhanced reliability and self compliance of synaptic arrays for multibit encoded neuromorphic systems
topic crossbar array
neuromorphic system
overshoot suppressed layer
resistive switching
self‐compliance
url https://doi.org/10.1002/aelm.202400282
work_keys_str_mv AT sungjoonkim enhancedreliabilityandselfcomplianceofsynapticarraysformultibitencodedneuromorphicsystems
AT hyeonseungji enhancedreliabilityandselfcomplianceofsynapticarraysformultibitencodedneuromorphicsystems
AT sungjunkim enhancedreliabilityandselfcomplianceofsynapticarraysformultibitencodedneuromorphicsystems
AT wooyoungchoi enhancedreliabilityandselfcomplianceofsynapticarraysformultibitencodedneuromorphicsystems