发布求助
文献互助 智能选刊 最新文献

2021 International Conference on Neuromorphic Computing (ICNC)最新文献

筛选
英文 中文
Zero-Hopf bifurcation of a reaction-diffusion memristive BAM neural network with time delay 一类时滞反应扩散记忆性BAM神经网络的零hopf分岔
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608817
Yang Wang, Tao Dong, Nankun Mu
{"title":"Zero-Hopf bifurcation of a reaction-diffusion memristive BAM neural network with time delay","authors":"Yang Wang, Tao Dong, Nankun Mu","doi":"10.1109/icnc52316.2021.9608817","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608817","url":null,"abstract":"In this paper, a reaction-diffusion memristive BAM neural network with time delay is constructed. Then, the zero-Hopf bifurcation conditions are obtained and the third-order normal form of zero-Hopf bifurcation are obtained by using the center manifold theorem and the normal form theory. Through analysing the normal form, the dynamic regions on coupling strength of memristor and time dealy plane are obtained, which has six regions. Some interesting dynamics are found in these areas.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123014914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An inertial neuro-dynamic system for solving zero-one integer programming 求解0 - 1整数规划的惯性神经动力学系统
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608378
Shuting Wei, Xing He
{"title":"An inertial neuro-dynamic system for solving zero-one integer programming","authors":"Shuting Wei, Xing He","doi":"10.1109/icnc52316.2021.9608378","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608378","url":null,"abstract":"This paper presents an inertial neuro-dynamic system to solve zero-one integer programming. We transform the problem of zero-one integer programming into a relatively easy problem only subject to linear equality constraints by using a nonlinear complementarity problem function. Subsequently, a inertial neuro-dynamic system is proposed to solve above transformed problem. It is shown that the proposed inertial neuro-dynamic system is stable and the equilibrium point converges to optimal solution set. It is worth emphasizing that our developed inertial neuro-dynamic system achieves faster convergence speed and explores more optimal solutions in a fixed initial value by adjusting the inertial factor. Finally, according to the experimental results on two illustrative examples, the proposed method is highly effective.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125275694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An image classification method based on Echo State Network 基于回声状态网络的图像分类方法
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9607999
Jingyu Sun, Lixiang Li, Haipeng Peng
{"title":"An image classification method based on Echo State Network","authors":"Jingyu Sun, Lixiang Li, Haipeng Peng","doi":"10.1109/icnc52316.2021.9607999","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9607999","url":null,"abstract":"As a traditional neural network architecture, Echo State Network(ESN) has achieved good results in time series forecasting. However, in the past ten years, few people have conducted research on its application to images, especially in classification tasks. Echo State Network is a kind of Recurrent Neural Network, it has the advantages of simple structure and convenient training. It only needs to train its output weight $w_{out}$, which saves a lot of time and resources. In this article, we input the whole picture into ESN in multi-input mode to classify images, and use the traditional Long Short-Term Memory(LSTM) model to compare experiments with it, and the results found that esn has better stability and accuracy.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132618482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Detection of Stealthy Cyber-attack in Distributed DC Microgrids Based on LSTM Neural Network 基于LSTM神经网络的分布式直流微电网隐身网络攻击检测
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608150
Xingquan Fu, Mengfei Niu, G. Wen
{"title":"Detection of Stealthy Cyber-attack in Distributed DC Microgrids Based on LSTM Neural Network","authors":"Xingquan Fu, Mengfei Niu, G. Wen","doi":"10.1109/icnc52316.2021.9608150","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608150","url":null,"abstract":"Distributed DC microgrids, which mainly consist of cyber layer and physical layer, can be classified as a classical cyber-physical system. Compared with the physical layer, the cyber layer has a significant risk of malicious cyber-attack due to its inherent vulnerability. This paper investigates a lightweight cyber-attack detection problem for distributed DC microgrids with bounded process and measurement noises. More precisely, the cyber-attack under consideration is assumed to be the stealthy cyber-attack. A long short-term memory (LSTM) neural network-based strategy is proposed to construct the attack detection scheme without using the information of the noises. Case studies indicate that the proposed attack detection strategy can work effectively in the following two cases: i) the statistical characteristics of system noises are unknown; ii) the magnitude of the cyber-attack is lightweight, which is detected extremely hard by traditional detectors such as $chi^{2}$ detector.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131890147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Anti-synchronization of Multi-Weighted Coupled Complex-Valued Delayed Memristive Neural Networks with Coupling Delays 具有耦合时滞的多重加权耦合复值延迟记忆性神经网络的反同步
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608133
Limei Su, Yanli Huang, Jinliang Wang
{"title":"Anti-synchronization of Multi-Weighted Coupled Complex-Valued Delayed Memristive Neural Networks with Coupling Delays","authors":"Limei Su, Yanli Huang, Jinliang Wang","doi":"10.1109/icnc52316.2021.9608133","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608133","url":null,"abstract":"This paper studies anti-synchronization of multi-weighted coupled complex-valued delayed memristive neural networks (MWCCVDMNNs) with coupling delays. We derive a criterion for guaranteeing anti-synchronization of MWCCVDMNNs with coupling delays, by means of Lyapunov functional method and designing an appropriate controller. Moreover, a numerical example is given to verify the correctness of the obtained theoretical result.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115456738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Impulsive Consensus Algorithms for Second-order Multi-agent Formation Based on the Improved Artificial Potential Field 基于改进人工势场的二阶多智能体形成脉冲一致算法
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608859
Yijie Qin, Zhiwei Liu, Lei Fu, Z. Dong, Qihai Sun, Dingxin He
{"title":"Impulsive Consensus Algorithms for Second-order Multi-agent Formation Based on the Improved Artificial Potential Field","authors":"Yijie Qin, Zhiwei Liu, Lei Fu, Z. Dong, Qihai Sun, Dingxin He","doi":"10.1109/icnc52316.2021.9608859","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608859","url":null,"abstract":"In this paper, the impulsive consensus problem for second-order multi-agent formation based on the improved artificial potential field (APF) is investigated. In order to control the agent, the motion model of the Mecanum wheel trolley is established. In order to realize the consensus of multi-agent system, a second-order impulsive model is used to control the formation. To avoid collisions during formation establishment, the improved APF method is introduced and applied, and the repulsive force field and attractive field potential function are improved to solve the local minimum value and target unreachable problems of APF. Finally, the simulation and experiment show the effectiveness of the proposed control algorithm.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116656850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Memristor-based Echo State Network and Prediction for Time Series 基于忆阻器的回声状态网络及时间序列预测
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608158
Xiaohui Mu, Lixiang Li
{"title":"Memristor-based Echo State Network and Prediction for Time Series","authors":"Xiaohui Mu, Lixiang Li","doi":"10.1109/icnc52316.2021.9608158","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608158","url":null,"abstract":"This paper proposes echo state network based on the memristor and applies it to the prediction of chaotic time series. The memristor is used to replace the connection synapses between neurons in the echo state network reservoir, which improves the prediction performance of the network. A simulation experiment is carried out on the echo state network based on the memristor in the widely used chaotic time series prediction. The experiment results show that the echo state network based on the memristor improves the prediction accuracy and performance of the network.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123502824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fixed-/Preassigned-Time Stabilization of Memristive Neural Networks with Discontinuous Activations 不连续激活记忆神经网络的固定/预分配时间镇定
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608576
Haoyu Li, Leimin Wang
{"title":"Fixed-/Preassigned-Time Stabilization of Memristive Neural Networks with Discontinuous Activations","authors":"Haoyu Li, Leimin Wang","doi":"10.1109/icnc52316.2021.9608576","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608576","url":null,"abstract":"In this paper, the fixed-time stabilization (FTS) and preassigned-time stabilization (PTS) problems for memristive neural networks (MNNs) with discontinuous activation functions (DAF) is investigated by designing a unified controller. In addition, less conservative stabilization criteria are derived to ensure the FTS and PTS of MNNs. Besides, a more accurate estimate of settling time is obtained based on Lyapunov stability theory. Finally, a numerical simulation is illustrated to verify the validity of theoretical results.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130991031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Memristor-based Brain-like Reconfigurable Neuromorphic System 基于忆阻器的类脑可重构神经形态系统
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608461
Le Yang, Zhixia Ding, Hongfei Liu, Yanyang Xu, Ting Su
{"title":"Memristor-based Brain-like Reconfigurable Neuromorphic System","authors":"Le Yang, Zhixia Ding, Hongfei Liu, Yanyang Xu, Ting Su","doi":"10.1109/icnc52316.2021.9608461","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608461","url":null,"abstract":"It improves the data processing performance and efficiency notably that the memristor-based neuromorphic system is constructed by mimicking the features of brain. This paper proposes a memristor-based circuit implementation for brain-like reconfigurable neuromorphic system. This neuromorphic system contains memristor-based back-propagation neural network, memristor-based long short-term memory network, and memristor-based associative memory network. The reconfigurable circuit components can constitute the circuit hardware of the three memristor-based networks according to the task requirements or release the circuit hardware of the three memristor-based networks based on the forgetting mechanism along with time of the biology. Hence, this neuromorphic system has dynamic topology structure, which is similar as the feature of biological neural networks. A case study of the memristor-based brain-like reconfigurable neuromorphic system is presented in the paper. In the case study, the memristor-based back-propagation neural network and the memristor-based long short-term memory network are applied for the image recognition and speech recognition, respectively. The recognition results of the two memristor-based networks are input to the memristor-based associative memory network to recall the correlated information. This neuromorphic system has the potential to apply for the intelligent robot system.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131400166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Stability of Inertial Delayed Neural Networks Via Event-Triggered Impulsive Control 基于事件触发脉冲控制的惯性延迟神经网络稳定性研究
2021 International Conference on Neuromorphic Computing (ICNC) Pub Date : 2021-10-15 DOI: 10.1109/icnc52316.2021.9608314
Nan Hong, Wei Zhang, Tianguang Zhang
{"title":"Stability of Inertial Delayed Neural Networks Via Event-Triggered Impulsive Control","authors":"Nan Hong, Wei Zhang, Tianguang Zhang","doi":"10.1109/icnc52316.2021.9608314","DOIUrl":"https://doi.org/10.1109/icnc52316.2021.9608314","url":null,"abstract":"This paper studies the stability of inertial delayed neural networks via event-triggered impulsive control (ETIC), where impulsive instants are determined by an effective Lyapunov-based impulsive event triggered mechanism (IETM). Based on the IETM, the Zeno behavior is excluded and ensures the globally exponential stability and h-stability of the neural networks by constructing Lyapunov function and some different restrictive conditions. In addition, the delay term in inertial neural networks is well dealt with the two lemmas given in this paper. It is shown that inertial delayed neural networks can be stabilized through this event-triggered impulsive control. Finally, two numerical examples and their simulations are carried out to verify the effectiveness of this method.","PeriodicalId":412866,"journal":{"name":"2021 International Conference on Neuromorphic Computing (ICNC)","volume":"154 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122496965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页 下一页 尾页
0
×
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
请完成安全验证×
相关产品
×
本文献相关产品
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
小红书