在神经形态芯片中实现用于信息检索的张量组织记忆

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS Computers Pub Date : 2023-09-22 DOI:10.3390/computers12100189
Arash Khajooei Nejad, Mohammad (Behdad) Jamshidi, Shahriar B. Shokouhi
{"title":"在神经形态芯片中实现用于信息检索的张量组织记忆","authors":"Arash Khajooei Nejad, Mohammad (Behdad) Jamshidi, Shahriar B. Shokouhi","doi":"10.3390/computers12100189","DOIUrl":null,"url":null,"abstract":"This paper introduces Tensor-Organized Memory (TOM), a novel neuromorphic architecture inspired by the human brain’s structural and functional principles. Utilizing spike-timing-dependent plasticity (STDP) and Hebbian rules, TOM exhibits cognitive behaviors similar to the human brain. Compared to conventional architectures using a simplified leaky integrate-and-fire (LIF) neuron model, TOM showcases robust performance, even in noisy conditions. TOM’s adaptability and unique organizational structure, rooted in the Columnar-Organized Memory (COM) framework, position it as a transformative digital memory processing solution. Innovative neural architecture, advanced recognition mechanisms, and integration of synaptic plasticity rules enhance TOM’s cognitive capabilities. We have compared the TOM architecture with a conventional floating-point architecture, using a simplified LIF neuron model. We also implemented tests with varying noise levels and partially erased messages to evaluate its robustness. Despite the slight degradation in performance with noisy messages beyond 30%, the TOM architecture exhibited appreciable performance under less-than-ideal conditions. This exploration into the TOM architecture reveals its potential as a framework for future neuromorphic systems. This study lays the groundwork for future applications in implementing neuromorphic chips for high-performance intelligent edge devices, thereby revolutionizing industries and enhancing user experiences within the power of artificial intelligence.","PeriodicalId":46292,"journal":{"name":"Computers","volume":"33 1","pages":"0"},"PeriodicalIF":2.6000,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Implementing Tensor-Organized Memory for Message Retrieval Purposes in Neuromorphic Chips\",\"authors\":\"Arash Khajooei Nejad, Mohammad (Behdad) Jamshidi, Shahriar B. Shokouhi\",\"doi\":\"10.3390/computers12100189\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper introduces Tensor-Organized Memory (TOM), a novel neuromorphic architecture inspired by the human brain’s structural and functional principles. Utilizing spike-timing-dependent plasticity (STDP) and Hebbian rules, TOM exhibits cognitive behaviors similar to the human brain. Compared to conventional architectures using a simplified leaky integrate-and-fire (LIF) neuron model, TOM showcases robust performance, even in noisy conditions. TOM’s adaptability and unique organizational structure, rooted in the Columnar-Organized Memory (COM) framework, position it as a transformative digital memory processing solution. Innovative neural architecture, advanced recognition mechanisms, and integration of synaptic plasticity rules enhance TOM’s cognitive capabilities. We have compared the TOM architecture with a conventional floating-point architecture, using a simplified LIF neuron model. We also implemented tests with varying noise levels and partially erased messages to evaluate its robustness. Despite the slight degradation in performance with noisy messages beyond 30%, the TOM architecture exhibited appreciable performance under less-than-ideal conditions. This exploration into the TOM architecture reveals its potential as a framework for future neuromorphic systems. This study lays the groundwork for future applications in implementing neuromorphic chips for high-performance intelligent edge devices, thereby revolutionizing industries and enhancing user experiences within the power of artificial intelligence.\",\"PeriodicalId\":46292,\"journal\":{\"name\":\"Computers\",\"volume\":\"33 1\",\"pages\":\"0\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2023-09-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/computers12100189\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/computers12100189","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

摘要

张量组织记忆(Tensor-Organized Memory, TOM)是一种受人脑结构和功能原理启发的新型神经形态结构。利用spike- time -dependent plasticity (STDP)和Hebbian规则,TOM表现出与人类大脑相似的认知行为。与使用简化的泄漏集成与火灾(LIF)神经元模型的传统架构相比,TOM即使在噪声条件下也表现出鲁棒性。TOM的适应性和独特的组织结构植根于柱状组织存储器(COM)框架,使其成为一种变革性的数字存储器处理解决方案。创新的神经结构、先进的识别机制和突触可塑性规则的整合增强了TOM的认知能力。我们使用简化的LIF神经元模型将TOM架构与传统的浮点架构进行了比较。我们还实现了具有不同噪声水平和部分擦除消息的测试,以评估其稳健性。尽管噪声消息超过30%时性能会略有下降,但TOM架构在不太理想的条件下表现出可观的性能。对TOM架构的探索揭示了它作为未来神经形态系统框架的潜力。这项研究为高性能智能边缘设备实现神经形态芯片的未来应用奠定了基础,从而在人工智能的力量下彻底改变行业并增强用户体验。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Implementing Tensor-Organized Memory for Message Retrieval Purposes in Neuromorphic Chips
This paper introduces Tensor-Organized Memory (TOM), a novel neuromorphic architecture inspired by the human brain’s structural and functional principles. Utilizing spike-timing-dependent plasticity (STDP) and Hebbian rules, TOM exhibits cognitive behaviors similar to the human brain. Compared to conventional architectures using a simplified leaky integrate-and-fire (LIF) neuron model, TOM showcases robust performance, even in noisy conditions. TOM’s adaptability and unique organizational structure, rooted in the Columnar-Organized Memory (COM) framework, position it as a transformative digital memory processing solution. Innovative neural architecture, advanced recognition mechanisms, and integration of synaptic plasticity rules enhance TOM’s cognitive capabilities. We have compared the TOM architecture with a conventional floating-point architecture, using a simplified LIF neuron model. We also implemented tests with varying noise levels and partially erased messages to evaluate its robustness. Despite the slight degradation in performance with noisy messages beyond 30%, the TOM architecture exhibited appreciable performance under less-than-ideal conditions. This exploration into the TOM architecture reveals its potential as a framework for future neuromorphic systems. This study lays the groundwork for future applications in implementing neuromorphic chips for high-performance intelligent edge devices, thereby revolutionizing industries and enhancing user experiences within the power of artificial intelligence.
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
Computers
Computers COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS-
CiteScore
5.40
自引率
3.60%
发文量
153
审稿时长
11 weeks
期刊最新文献
Advanced Road Safety: Collective Perception for Probability of Collision Estimation of Connected Vehicles Forecasting of Bitcoin Illiquidity Using High-Dimensional and Textual Features Mining Negative Associations from Medical Databases Considering Frequent, Regular, Closed and Maximal Patterns Faraway, so Close: Perceptions of the Metaverse on the Edge of Madness Blockchain-Powered Gaming: Bridging Entertainment with Serious Game Objectives
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1