256‐level honey memristor‐based in‐memory neuromorphic system

Abstract Promising synaptic behaviour has been exhibited by memristors based on natural organic materials. Such memristor‐based neuromorphic systems offer notable benefits, including environmental sustainability, low production and disposal costs, non‐volatile storage capability, and bio/Complementa...

Full description

Saved in:
Bibliographic Details
Main Authors: Harshvardhan Uppaluru, Zoe Templin, Mohammed Rafeeq Khan, Md Omar Faruque, Feng Zhao, Jinhui Wang
Format: Article
Language:English
Published: Wiley 2024-09-01
Series:Electronics Letters
Subjects:
Online Access:https://doi.org/10.1049/ell2.70029
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850193072202186752
author Harshvardhan Uppaluru
Zoe Templin
Mohammed Rafeeq Khan
Md Omar Faruque
Feng Zhao
Jinhui Wang
author_facet Harshvardhan Uppaluru
Zoe Templin
Mohammed Rafeeq Khan
Md Omar Faruque
Feng Zhao
Jinhui Wang
author_sort Harshvardhan Uppaluru
collection DOAJ
description Abstract Promising synaptic behaviour has been exhibited by memristors based on natural organic materials. Such memristor‐based neuromorphic systems offer notable benefits, including environmental sustainability, low production and disposal costs, non‐volatile storage capability, and bio/Complementary Metal‐Oxide‐Semiconductor (CMOS) compatibility. Here, a 256‐level honey memristor‐based neuromorphic system is experimentally evaluated for image recognition. In detail, first, 256‐level honey memristors are manufactured and tested based on in‐house technology; next, the non‐linear characteristics and inherent variation of honey memristor devices, which lead to imprecise weight updates and limit the inference accuracy, are investigated. Experimental results indicate that the inference accuracy of the 256‐level honey memristor‐based neuromorphic system is greater than 88% without cycle‐to‐cycle variations and 87% with cycle‐to‐cycle variations for different optimization algorithms. The overall performance of optimization algorithms with and without variation is compared in terms of energy and latency, where the momentum algorithm consistently outperforms the rest of the algorithms. This 256‐level honey memristor is a promising alternative enabling sustainable neuromorphic systems, encouraging further research into natural organic materials for neuromorphic computing.
format Article
id doaj-art-d03b45568d894a9c93f549d8a77ea4e1
institution OA Journals
issn 0013-5194
1350-911X
language English
publishDate 2024-09-01
publisher Wiley
record_format Article
series Electronics Letters
spelling doaj-art-d03b45568d894a9c93f549d8a77ea4e12025-08-20T02:14:22ZengWileyElectronics Letters0013-51941350-911X2024-09-016017n/an/a10.1049/ell2.70029256‐level honey memristor‐based in‐memory neuromorphic systemHarshvardhan Uppaluru0Zoe Templin1Mohammed Rafeeq Khan2Md Omar Faruque3Feng Zhao4Jinhui Wang5Department of Electrical and Computer EngineeringUniversity of South AlabamaMobileAlabamaUSASchool of Engineering and Computer ScienceWashington State UniversityVancouverWashingtonUSADepartment of Electrical and Computer EngineeringUniversity of South AlabamaMobileAlabamaUSADepartment of Electrical and Computer EngineeringUniversity of South AlabamaMobileAlabamaUSASchool of Engineering and Computer ScienceWashington State UniversityVancouverWashingtonUSADepartment of Electrical and Computer EngineeringUniversity of South AlabamaMobileAlabamaUSAAbstract Promising synaptic behaviour has been exhibited by memristors based on natural organic materials. Such memristor‐based neuromorphic systems offer notable benefits, including environmental sustainability, low production and disposal costs, non‐volatile storage capability, and bio/Complementary Metal‐Oxide‐Semiconductor (CMOS) compatibility. Here, a 256‐level honey memristor‐based neuromorphic system is experimentally evaluated for image recognition. In detail, first, 256‐level honey memristors are manufactured and tested based on in‐house technology; next, the non‐linear characteristics and inherent variation of honey memristor devices, which lead to imprecise weight updates and limit the inference accuracy, are investigated. Experimental results indicate that the inference accuracy of the 256‐level honey memristor‐based neuromorphic system is greater than 88% without cycle‐to‐cycle variations and 87% with cycle‐to‐cycle variations for different optimization algorithms. The overall performance of optimization algorithms with and without variation is compared in terms of energy and latency, where the momentum algorithm consistently outperforms the rest of the algorithms. This 256‐level honey memristor is a promising alternative enabling sustainable neuromorphic systems, encouraging further research into natural organic materials for neuromorphic computing.https://doi.org/10.1049/ell2.70029artificial intelligencememristors
spellingShingle Harshvardhan Uppaluru
Zoe Templin
Mohammed Rafeeq Khan
Md Omar Faruque
Feng Zhao
Jinhui Wang
256‐level honey memristor‐based in‐memory neuromorphic system
Electronics Letters
artificial intelligence
memristors
title 256‐level honey memristor‐based in‐memory neuromorphic system
title_full 256‐level honey memristor‐based in‐memory neuromorphic system
title_fullStr 256‐level honey memristor‐based in‐memory neuromorphic system
title_full_unstemmed 256‐level honey memristor‐based in‐memory neuromorphic system
title_short 256‐level honey memristor‐based in‐memory neuromorphic system
title_sort 256 level honey memristor based in memory neuromorphic system
topic artificial intelligence
memristors
url https://doi.org/10.1049/ell2.70029
work_keys_str_mv AT harshvardhanuppaluru 256levelhoneymemristorbasedinmemoryneuromorphicsystem
AT zoetemplin 256levelhoneymemristorbasedinmemoryneuromorphicsystem
AT mohammedrafeeqkhan 256levelhoneymemristorbasedinmemoryneuromorphicsystem
AT mdomarfaruque 256levelhoneymemristorbasedinmemoryneuromorphicsystem
AT fengzhao 256levelhoneymemristorbasedinmemoryneuromorphicsystem
AT jinhuiwang 256levelhoneymemristorbasedinmemoryneuromorphicsystem