基于受限玻尔兹曼机的传感器内视觉系统的随机光响应记忆神经元

IF 8 2区 材料科学 Q1 CHEMISTRY, PHYSICAL
Jin Hong Kim, Hyun Wook Kim, Min Jung Chung, Dong Hoon Shin, Yeong Rok Kim, Jaehyun Kim, Yoon Ho Jang, Sun Woo Cheong, Soo Hyung Lee, Janguk Han, Hyung Jun Park, Joon-Kyu Han and Cheol Seong Hwang
{"title":"基于受限玻尔兹曼机的传感器内视觉系统的随机光响应记忆神经元","authors":"Jin Hong Kim, Hyun Wook Kim, Min Jung Chung, Dong Hoon Shin, Yeong Rok Kim, Jaehyun Kim, Yoon Ho Jang, Sun Woo Cheong, Soo Hyung Lee, Janguk Han, Hyung Jun Park, Joon-Kyu Han and Cheol Seong Hwang","doi":"10.1039/D4NH00421C","DOIUrl":null,"url":null,"abstract":"<p >In-sensor computing has gained attention as a solution to overcome the von Neumann computing bottlenecks inherent in conventional sensory systems. This attention is due to the ability of sensor elements to directly extract meaningful information from external signals, thereby simplifying complex data. The advantage of in-sensor computing can be maximized with the sampling principle of a restricted Boltzmann machine (RBM) to extract significant features. In this study, a stochastic photo-responsive neuron is developed using a TiN/In–Ga–Zn–O/TiN optoelectronic memristor and an Ag/HfO<small><sub>2</sub></small>/Pt threshold-switching memristor, which can be configured as an input neuron in an in-sensor RBM. It demonstrates a sigmoidal switching probability depending on light intensity. The stochastic properties allow for the simultaneous exploration of various neuron states within the network, making identifying optimal features in complex images easier. Based on semi-empirical simulations, high recognition accuracies of 90.9% and 95.5% are achieved using handwritten digit and face image datasets, respectively. In addition, the in-sensor RBM effectively reconstructs abnormal face images, indicating that integrating in-sensor computing with probabilistic neural networks can lead to reliable and efficient image recognition under unpredictable real-world conditions.</p>","PeriodicalId":93,"journal":{"name":"Nanoscale Horizons","volume":" 12","pages":" 2248-2258"},"PeriodicalIF":8.0000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A stochastic photo-responsive memristive neuron for an in-sensor visual system based on a restricted Boltzmann machine†\",\"authors\":\"Jin Hong Kim, Hyun Wook Kim, Min Jung Chung, Dong Hoon Shin, Yeong Rok Kim, Jaehyun Kim, Yoon Ho Jang, Sun Woo Cheong, Soo Hyung Lee, Janguk Han, Hyung Jun Park, Joon-Kyu Han and Cheol Seong Hwang\",\"doi\":\"10.1039/D4NH00421C\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >In-sensor computing has gained attention as a solution to overcome the von Neumann computing bottlenecks inherent in conventional sensory systems. This attention is due to the ability of sensor elements to directly extract meaningful information from external signals, thereby simplifying complex data. The advantage of in-sensor computing can be maximized with the sampling principle of a restricted Boltzmann machine (RBM) to extract significant features. In this study, a stochastic photo-responsive neuron is developed using a TiN/In–Ga–Zn–O/TiN optoelectronic memristor and an Ag/HfO<small><sub>2</sub></small>/Pt threshold-switching memristor, which can be configured as an input neuron in an in-sensor RBM. It demonstrates a sigmoidal switching probability depending on light intensity. The stochastic properties allow for the simultaneous exploration of various neuron states within the network, making identifying optimal features in complex images easier. Based on semi-empirical simulations, high recognition accuracies of 90.9% and 95.5% are achieved using handwritten digit and face image datasets, respectively. In addition, the in-sensor RBM effectively reconstructs abnormal face images, indicating that integrating in-sensor computing with probabilistic neural networks can lead to reliable and efficient image recognition under unpredictable real-world conditions.</p>\",\"PeriodicalId\":93,\"journal\":{\"name\":\"Nanoscale Horizons\",\"volume\":\" 12\",\"pages\":\" 2248-2258\"},\"PeriodicalIF\":8.0000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nanoscale Horizons\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://pubs.rsc.org/en/content/articlelanding/2024/nh/d4nh00421c\",\"RegionNum\":2,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nanoscale Horizons","FirstCategoryId":"88","ListUrlMain":"https://pubs.rsc.org/en/content/articlelanding/2024/nh/d4nh00421c","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

摘要

传感内计算作为克服传统传感系统固有的冯-诺依曼计算瓶颈的一种解决方案,已受到广泛关注。之所以受到关注,是因为传感器元件能够直接从外部信号中提取有意义的信息,从而简化复杂的数据。利用受限玻尔兹曼机(RBM)的采样原理提取重要特征,可以最大限度地发挥传感器内计算的优势。本研究利用 TiN/In-Ga-Zn-O/TiN 光电忆阻器和 Ag/HfO2/Pt 阈值开关忆阻器开发了一种随机光响应神经元,可将其配置为传感器内 RBM 的输入神经元。它的开关概率随光照强度的不同而呈正弦曲线变化。随机特性允许同时探索网络中的各种神经元状态,从而更容易识别复杂图像中的最佳特征。在半经验模拟的基础上,利用手写数字和人脸图像数据集分别实现了 90.9% 和 95.5% 的高识别准确率。此外,传感器内 RBM 还能有效重建异常人脸图像,这表明将传感器内计算与概率神经网络相结合,能在不可预测的真实世界条件下实现可靠、高效的图像识别。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

A stochastic photo-responsive memristive neuron for an in-sensor visual system based on a restricted Boltzmann machine†

A stochastic photo-responsive memristive neuron for an in-sensor visual system based on a restricted Boltzmann machine†

In-sensor computing has gained attention as a solution to overcome the von Neumann computing bottlenecks inherent in conventional sensory systems. This attention is due to the ability of sensor elements to directly extract meaningful information from external signals, thereby simplifying complex data. The advantage of in-sensor computing can be maximized with the sampling principle of a restricted Boltzmann machine (RBM) to extract significant features. In this study, a stochastic photo-responsive neuron is developed using a TiN/In–Ga–Zn–O/TiN optoelectronic memristor and an Ag/HfO2/Pt threshold-switching memristor, which can be configured as an input neuron in an in-sensor RBM. It demonstrates a sigmoidal switching probability depending on light intensity. The stochastic properties allow for the simultaneous exploration of various neuron states within the network, making identifying optimal features in complex images easier. Based on semi-empirical simulations, high recognition accuracies of 90.9% and 95.5% are achieved using handwritten digit and face image datasets, respectively. In addition, the in-sensor RBM effectively reconstructs abnormal face images, indicating that integrating in-sensor computing with probabilistic neural networks can lead to reliable and efficient image recognition under unpredictable real-world conditions.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Nanoscale Horizons
Nanoscale Horizons Materials Science-General Materials Science
CiteScore
16.30
自引率
1.00%
发文量
141
期刊介绍: Nanoscale Horizons stands out as a premier journal for publishing exceptionally high-quality and innovative nanoscience and nanotechnology. The emphasis lies on original research that introduces a new concept or a novel perspective (a conceptual advance), prioritizing this over reporting technological improvements. Nevertheless, outstanding articles showcasing truly groundbreaking developments, including record-breaking performance, may also find a place in the journal. Published work must be of substantial general interest to our broad and diverse readership across the nanoscience and nanotechnology community.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信