发布求助
文献互助 智能选刊 最新文献

1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)最新文献

筛选
英文 中文
A 0.5 /spl mu/m CMOS CNN analog random access memory chip for massive image processing 一种用于大规模图像处理的0.5 /spl μ m CMOS CNN模拟随机存取存储器芯片
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685386
R. Carmona, S. Espejo, R. Domínguez-Castro, A. Rodriguez-Vazque., T. Roska, T. Kozek, L. Chua
{"title":"A 0.5 /spl mu/m CMOS CNN analog random access memory chip for massive image processing","authors":"R. Carmona, S. Espejo, R. Domínguez-Castro, A. Rodriguez-Vazque., T. Roska, T. Kozek, L. Chua","doi":"10.1109/CNNA.1998.685386","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685386","url":null,"abstract":"An analog RAM has been designed to act as a cache memory for a CNN Universal Machine. Hence, all the non-standard chips are available for the CNN Chipset architecture. Time-multiplexed analog routines in the CNN processor require fast and efficient short-time signal storage in an analog buffer. This can be achieved by an extended sample and hold scheme able to address every sample to specific memory locations. Several arrays of capacitors are multiplexed sharing controlling circuitry and I/O buses. The design has the following key parameters: 637 analog memory cells/mm/sup 2/ with 0.4% accuracy, 100 ns access time and 170 ms storage time (within 1% error).","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125497526","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: 19
An application of cellular neural network maximum clique problem 细胞神经网络最大团问题的一个应用
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685365
N. Sengor, M. Yalçin, Y. Çakir, M. Ucer, C. Guzelis, F. Pekergin, O. Morgul
{"title":"An application of cellular neural network maximum clique problem","authors":"N. Sengor, M. Yalçin, Y. Çakir, M. Ucer, C. Guzelis, F. Pekergin, O. Morgul","doi":"10.1109/CNNA.1998.685365","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685365","url":null,"abstract":"An approximate solution to an NP-hard discrete optimization problem, namely finding maximum clique, is given using cellular neural networks. Even though the problem is defined by discrete variables, a continuous cellular network is used. The maximal cliques are the stable states of the cellular neural networks. To illustrate the performance of the method, the results are compared with some existing models as saturated linear dynamical network continuous Hopfield dynamics.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125926131","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
Image processing using time-varying cellular neural networks 时变细胞神经网络的图像处理
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685394
N.N. Kamiss Al-Ani, T. Kacprzak
{"title":"Image processing using time-varying cellular neural networks","authors":"N.N. Kamiss Al-Ani, T. Kacprzak","doi":"10.1109/CNNA.1998.685394","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685394","url":null,"abstract":"Properties of cellular neural networks with time-varying gain of cells in the linear part of the transfer function are studied. It is shown that this concept of the CNN dynamics provides new interesting results of image processing tasks which can be used to improve the performance. This aspect is of great importance for the design of VLSI implemented CNN chips. The new properties are documented by the theoretical analysis and computer simulations of three examples.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129897609","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: 8
Dynamic circular cellular networks for adaptive smoothing of multi-dimensional signals 多维信号自适应平滑的动态圆细胞网络
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685393
K. Wiehler, R. Lembcke, R. Grigat, J. Heers, C. Schnorr, H. Stiehl
{"title":"Dynamic circular cellular networks for adaptive smoothing of multi-dimensional signals","authors":"K. Wiehler, R. Lembcke, R. Grigat, J. Heers, C. Schnorr, H. Stiehl","doi":"10.1109/CNNA.1998.685393","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685393","url":null,"abstract":"In Schnorr et al. (1996) a theoretical framework for locally-adaptive smoothing of multi-dimensional data was presented. Based on this framework we introduce a hardware efficient architecture suitable for mixed-mode VLSI implementation. Substantial shortcomings of analogue implementations are overcome by connecting all cells in a circular structure: (i) influence of process parameter deviation, (ii) limited number of cells, (iii) input/output bottleneck. The connections between the analogue cells and the cells themselves are dynamically reconfigured. This results in a non-linear adaptive filter kernel which is shifted virtually over the signal vector of infinite length. A 1D prototype with 32 cells has been fabricated using 0.8 /spl mu/m CMOS-technology. The chip is fully functional with an overall error less than 1%; experimental results are presented in the paper.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117343020","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: 5
Classification systems based on neural networks
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685324
J. Nossek, R. Eigenmann, G. Papoutsis, W. Utschick
{"title":"Classification systems based on neural networks","authors":"J. Nossek, R. Eigenmann, G. Papoutsis, W. Utschick","doi":"10.1109/CNNA.1998.685324","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685324","url":null,"abstract":"Classification is a problem that appears in many real life applications. We describe the general case of multi-class classification, where the task of the classification system is to map an input vector x to one of K>2 given classes. This problem is split in many two-class classification problems, each of them describing a part of the whole problem. These are solved by neural networks, producing an intermediate output in a reference space, which is then decoded to the solution of the original problem. The methods described here are then applied to the handwritten character recognition problem to produce the results described later in the article. It is suspected that they also may be applied successfully in the context of the CNN paradigm and be implemented on a CNN-Universal Machine.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131515612","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: 4
A harmonic balance technique for the analysis of periodic attractors and their bifurcations in CNNs 一种用于分析cnn中周期吸引子及其分岔的谐波平衡技术
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685343
P. Civalleri, M. Gilli
{"title":"A harmonic balance technique for the analysis of periodic attractors and their bifurcations in CNNs","authors":"P. Civalleri, M. Gilli","doi":"10.1109/CNNA.1998.685343","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685343","url":null,"abstract":"The occurrence of periodic attractors in CNNs is investigated through a harmonic balance technique. It is shown that for a N-cell CNN described by the template [a/sub -1/, a/sub 0/, a/sub 1/], this technique leads to a set of 3N nonlinear equations, that can be reduced to 2N+1 equations through suitable algebraic manipulations. The technique allows to determine all the limit cycles and most of the bifurcation phenomena occurring in the network. The results are in good agreement with those observed by the time-simulation of the network.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132335180","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
Edge of spatio-temporal chaos in cellular nonlinear networks 元胞非线性网络的时空混沌边缘
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685341
A. Dmitriev, Y. Andreyev
{"title":"Edge of spatio-temporal chaos in cellular nonlinear networks","authors":"A. Dmitriev, Y. Andreyev","doi":"10.1109/CNNA.1998.685341","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685341","url":null,"abstract":"We investigate phenomena of the edge of spatially uniform chaotic mode and spatial temporal chaos in a lattice of chaotic 1D maps with only local connections. It is shown that in autonomous lattice with local connections, spatially uniform chaotic mode cannot exist if the Lyapunov exponent /spl lambda/ of the isolated chaotic map is greater than some critical value /spl lambda//sub cr/>0. We proposed a model of a lattice with a pacemaker and found a spatially uniform mode synchronous with the pacemaker, as well as a spatially uniform mode different from the pacemaker mode.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131051565","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
Fault tolerant CNN template design and optimization based on chip measurements 基于芯片测量的容错CNN模板设计与优化
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685415
P. Foldesy, L. Kék, T. Roska, Á. Zarándy, G. Bártfai
{"title":"Fault tolerant CNN template design and optimization based on chip measurements","authors":"P. Foldesy, L. Kék, T. Roska, Á. Zarándy, G. Bártfai","doi":"10.1109/CNNA.1998.685415","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685415","url":null,"abstract":"Proposes a generic method for finding non-propagating cellular neural network (CNN) templates that can be implemented reliably on a given CNN Universal Machine chip. The method has two main components: (i) adaptive optimization of templates based on measurements of actual CNN chips, (ii) simplification and decomposition of Boolean operators into a sequence of simpler ones that work correctly and more robustly on a given chip. Examples are presented using two stored-program CNNUM chips to demonstrate the effectiveness of the proposed method, whose advantages and limitations are also discussed.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125416351","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: 6
Self-organization in cellular neural networks: a comparison with Kohonen's self-organizing maps 细胞神经网络中的自组织:与Kohonen自组织图的比较
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685332
Patrick Thiran
{"title":"Self-organization in cellular neural networks: a comparison with Kohonen's self-organizing maps","authors":"Patrick Thiran","doi":"10.1109/CNNA.1998.685332","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685332","url":null,"abstract":"The ordinary differential equation (ODE) method is difficult to use for analyzing the self-organization of the Kohonen algorithm. Two stochastic, 'self-organizing' algorithms, whose corresponding ODE is a CNN equation, are presented. Their convergence shares similar features with the Kohonen self-organizing process.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126610663","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: 3
Coexistence of attractors in a one-dimensional CNN array 一维CNN数组中吸引子的共存
1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359) Pub Date : 1998-04-14 DOI: 10.1109/CNNA.1998.685346
Z. Galias, M. Ogorzałek
{"title":"Coexistence of attractors in a one-dimensional CNN array","authors":"Z. Galias, M. Ogorzałek","doi":"10.1109/CNNA.1998.685346","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685346","url":null,"abstract":"In this paper we investigate long-term (steady-state) behavior of a one-dimensional array of chaotic circuits for different connection strength. Using computer experiments we have confirmed the existence of a very large number of stable steady-states depending only on the initial conditions applied in the individual cells and on the connection strength. Of special interest is the coexistence of large amplitude periodic oscillations in some cells and chaotic oscillations in the others, that forms very complex spatial patterns.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1998-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127552157","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
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：481959085
Book学术官方微信