具有记忆性突触权的尖峰神经网络中硬件类多巴胺学习的建模

IF 0.8 Q3 Engineering
I. V. Alyaev, I. A. Surazhevsky, A. I. Iliasov, V. V. Rylkov, V. A. Demin
{"title":"具有记忆性突触权的尖峰神经网络中硬件类多巴胺学习的建模","authors":"I. V. Alyaev,&nbsp;I. A. Surazhevsky,&nbsp;A. I. Iliasov,&nbsp;V. V. Rylkov,&nbsp;V. A. Demin","doi":"10.1134/S263516762560052X","DOIUrl":null,"url":null,"abstract":"<p>A Verilog-A model of a spiking neural network is developed, and its dopamine-like learning is carried out in solving the problem of recognizing the simplest images. The necessity of using unipolar pulses from postsynaptic neurons to implement dynamic plasticity of the “bell-shaped” and “anti-bell-shaped” types, as well as the positive effect of the inhibitory layer of neurons on the operation of the system, is shown. A hardware and software complex implementing this neural network and the dynamics of changes in the conductivity window of a memristor synaptic connection obtained with its help when emulating different “dopamine levels” in a neuromorphic system are presented.</p>","PeriodicalId":716,"journal":{"name":"Nanotechnologies in Russia","volume":"20 3","pages":"373 - 380"},"PeriodicalIF":0.8000,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Modeling of Hardware Dopamine-Like Learning in a Spiking Neural Network with Memristive Synaptic Weights\",\"authors\":\"I. V. Alyaev,&nbsp;I. A. Surazhevsky,&nbsp;A. I. Iliasov,&nbsp;V. V. Rylkov,&nbsp;V. A. Demin\",\"doi\":\"10.1134/S263516762560052X\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>A Verilog-A model of a spiking neural network is developed, and its dopamine-like learning is carried out in solving the problem of recognizing the simplest images. The necessity of using unipolar pulses from postsynaptic neurons to implement dynamic plasticity of the “bell-shaped” and “anti-bell-shaped” types, as well as the positive effect of the inhibitory layer of neurons on the operation of the system, is shown. A hardware and software complex implementing this neural network and the dynamics of changes in the conductivity window of a memristor synaptic connection obtained with its help when emulating different “dopamine levels” in a neuromorphic system are presented.</p>\",\"PeriodicalId\":716,\"journal\":{\"name\":\"Nanotechnologies in Russia\",\"volume\":\"20 3\",\"pages\":\"373 - 380\"},\"PeriodicalIF\":0.8000,\"publicationDate\":\"2025-08-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nanotechnologies in Russia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://link.springer.com/article/10.1134/S263516762560052X\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nanotechnologies in Russia","FirstCategoryId":"1085","ListUrlMain":"https://link.springer.com/article/10.1134/S263516762560052X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Engineering","Score":null,"Total":0}
引用次数: 0

摘要

开发了一个峰值神经网络的Verilog-A模型,并在解决识别最简单图像的问题上进行了类似多巴胺的学习。证明了利用突触后神经元单极脉冲实现“钟形”和“反钟形”动态可塑性的必要性,以及神经元抑制层对系统运行的积极作用。本文介绍了实现该神经网络的硬件和软件复合体,以及在模拟神经形态系统中不同“多巴胺水平”时获得的忆阻器突触连接电导率窗口变化的动力学。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Modeling of Hardware Dopamine-Like Learning in a Spiking Neural Network with Memristive Synaptic Weights

Modeling of Hardware Dopamine-Like Learning in a Spiking Neural Network with Memristive Synaptic Weights

Modeling of Hardware Dopamine-Like Learning in a Spiking Neural Network with Memristive Synaptic Weights

A Verilog-A model of a spiking neural network is developed, and its dopamine-like learning is carried out in solving the problem of recognizing the simplest images. The necessity of using unipolar pulses from postsynaptic neurons to implement dynamic plasticity of the “bell-shaped” and “anti-bell-shaped” types, as well as the positive effect of the inhibitory layer of neurons on the operation of the system, is shown. A hardware and software complex implementing this neural network and the dynamics of changes in the conductivity window of a memristor synaptic connection obtained with its help when emulating different “dopamine levels” in a neuromorphic system are presented.

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
Nanotechnologies in Russia
Nanotechnologies in Russia NANOSCIENCE & NANOTECHNOLOGY-
CiteScore
1.20
自引率
0.00%
发文量
0
期刊介绍: Nanobiotechnology Reports publishes interdisciplinary research articles on fundamental aspects of the structure and properties of nanoscale objects and nanomaterials, polymeric and bioorganic molecules, and supramolecular and biohybrid complexes, as well as articles that discuss technologies for their preparation and processing, and practical implementation of products, devices, and nature-like systems based on them. The journal publishes original articles and reviews that meet the highest scientific quality standards in the following areas of science and technology studies: self-organizing structures and nanoassemblies; nanostructures, including nanotubes; functional and structural nanomaterials; polymeric, bioorganic, and hybrid nanomaterials; devices and products based on nanomaterials and nanotechnology; nanobiology and genetics, and omics technologies; nanobiomedicine and nanopharmaceutics; nanoelectronics and neuromorphic computing systems; neurocognitive systems and technologies; nanophotonics; natural science methods in a study of cultural heritage items; metrology, standardization, and monitoring in nanotechnology.
×
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:604180095
Book学术官方微信