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
Recent progress on logic and algorithms for optical neural networks (ONN) 光神经网络(ONN)的逻辑和算法研究进展
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.1998.685328
S. Andersson
{"title":"Recent progress on logic and algorithms for optical neural networks (ONN)","authors":"S. Andersson","doi":"10.1109/CNNA.1998.685328","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685328","url":null,"abstract":"Summary form only given. The need for optical implementations of neural networks is rooted in a number of obvious shortcomings of digital/electronic techniques. The author aims at giving at broad outline, in quite technical terms, of the state of the art in optical implementations. Special attention is paid to various types of logics, naturally attached to parallel data transportation by light. Algorithms built on these logics are presented through a number of examples the advantages, as well as disadvantages, of optical implementations are elucidated.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"258 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":"127362884","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: 13
A sufficient condition for the existence of a stable equilibrium point in nonsymmetric cellular neural networks 非对称细胞神经网络存在稳定平衡点的充分条件
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.1998.685333
S. Arik, V. Tavsanoglu
{"title":"A sufficient condition for the existence of a stable equilibrium point in nonsymmetric cellular neural networks","authors":"S. Arik, V. Tavsanoglu","doi":"10.1109/CNNA.1998.685333","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685333","url":null,"abstract":"We obtain a new sufficient condition for the existence of a stable equilibrium point in the total saturation region for nonsymmetric cellular neural networks (CNNs). It is shown that if the sum of the elements of each row of the feedback matrix is greater than one, a nonsymmetric CNN possesses a stable equilibrium point in the total saturation region.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"20 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":"115036971","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
Stochastic and hybrid approaches toward robust templates 稳健模板的随机和混合方法
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.1998.685403
M. Hanggi, G. Moschytz
{"title":"Stochastic and hybrid approaches toward robust templates","authors":"M. Hanggi, G. Moschytz","doi":"10.1109/CNNA.1998.685403","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685403","url":null,"abstract":"We propose and compare different methods of synthesizing robust templates for cellular neural networks. In the first approach, genetic algorithms are used for both template learning and optimization with respect to robustness. The evaluation of the fitness functions in the optimization step is computationally very expensive; a massively parallel supercomputer is used to achieve acceptable run times. As alternative approaches, a steepest-ascent method and an averaging approach are presented, the latter being computationally inexpensive. To overcome their respective drawbacks, these algorithms are combined into a hybrid approach which is shown to be efficient even for complex problems.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"39 2 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":"123927666","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: 12
A new current mode programmable cellular neural network 一种新的电流模式可编程细胞神经网络
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.1998.685380
L. Ravezzi, G. Dalla Betta, G. Setti
{"title":"A new current mode programmable cellular neural network","authors":"L. Ravezzi, G. Dalla Betta, G. Setti","doi":"10.1109/CNNA.1998.685380","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685380","url":null,"abstract":"We report on the design of a full-analog current-mode CNN in a 1.2 /spl mu/m CMOS technology, whose cell core is characterized by an intrinsic capability of weights control, low power consumption and small area occupation. Circuit simulations allowed the design approach to be validated and the electrical performance of the CNN to be predicted; moreover, it is shown that the proposed CNN can be successfully adopted for several applications in image processing. A preliminary CNN test-chip consisting of a 8/spl times/1 array for connected component detection and shadow detection, is currently being fabricated at IRST (Trento Italy) in a 2.5 /spl mu/m CMOS technology.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"44 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":"124498252","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
A CNN stereo vision hardware system for autonomous robot navigation 用于自主机器人导航的CNN立体视觉硬件系统
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.1998.685360
S. Taraglio, A. Zanela, M. Salerno, F. Sergeni, V. Bonaiuto
{"title":"A CNN stereo vision hardware system for autonomous robot navigation","authors":"S. Taraglio, A. Zanela, M. Salerno, F. Sergeni, V. Bonaiuto","doi":"10.1109/CNNA.1998.685360","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685360","url":null,"abstract":"The high parallel analogue processing rate makes the cellular neural networks paradigm really useful in such a problems where real-time replies to external stimuli are required. The development of an effective system for autonomous robot navigation can find a valid support from this research. Moreover, the growth of new CNN algorithms can afford the necessary feedback to the hardware developers to improve their realisations. In this paper some measurements of a stereo-vision algorithm on a CNN hardware implementation (the 720DPCNN system) are given.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"42 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":"115930934","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
Global asymptotic stability of discrete-time cellular neural networks 离散时间细胞神经网络的全局渐近稳定性
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.1998.685329
S. Arik, A. Kılınç, F. Acar Savaci
{"title":"Global asymptotic stability of discrete-time cellular neural networks","authors":"S. Arik, A. Kılınç, F. Acar Savaci","doi":"10.1109/CNNA.1998.685329","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685329","url":null,"abstract":"This paper presents two sufficient conditions for global stability of discrete-time cellular neural networks (DTCNNs). It is shown that if the first or second norm of the feedback matrix is smaller than one, then a DTCNN converges to a unique and globally asymptotically stable equilibrium point for every external input.","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":"124297111","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
Modeling almost incompressible fluid flow with CNN 用CNN模拟几乎不可压缩的流体流动
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.1998.685334
F. Puffer, R. Tetzlaff, D. Wolf
{"title":"Modeling almost incompressible fluid flow with CNN","authors":"F. Puffer, R. Tetzlaff, D. Wolf","doi":"10.1109/CNNA.1998.685334","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685334","url":null,"abstract":"A novel method for transferring the Navier-Stokes equations for two-dimensional almost incompressible, viscous flow to cellular neural network (CNN) is discussed. The problem has been treated previously by Kozek et al. (1994, 1995), where the CNN layer that represents the pressure had to perform on a much faster time-scale than the layers representing the velocity components. This is a drawback, especially when hardware realizations are considered. The method presented in this contribution avoids the use of a double time-scale CNN and requires fewer connections between the cells. The treatment of boundary conditions is discussed and the accuracy of the results is determined for two known analytical solutions.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"46 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":"126961801","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
Direct blind separation of independent non-Gaussian signals with dynamic channels 具有动态信道的独立非高斯信号的直接盲分离
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.1998.685325
Ruey-Wen Liu, Hui Luo
{"title":"Direct blind separation of independent non-Gaussian signals with dynamic channels","authors":"Ruey-Wen Liu, Hui Luo","doi":"10.1109/CNNA.1998.685325","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685325","url":null,"abstract":"A fundamental theorem of direct blind separation of independent non-Gaussian signals with dynamic channels is presented. Roughly, it states that blind signal separation is achieved if and only if the output signals are temporally uncorrelated and pairwise independent. This condition is simple enough to be adaptable by a neural network.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"29 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":"121263897","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: 20
On the absolute stability of delayed cellular neural networks 延迟细胞神经网络的绝对稳定性
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.1998.685338
M. Joy
{"title":"On the absolute stability of delayed cellular neural networks","authors":"M. Joy","doi":"10.1109/CNNA.1998.685338","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685338","url":null,"abstract":"This paper presents new (sufficient) conditions for the absolute stability of delayed cellular neural networks (CNNs) which improve on previously known ones. Importantly, we are able to give both necessary and sufficient conditions for the absolute stability of cooperative, delayed CNNs. We discuss these conditions with reference to the feedback and delay matrices, derive specific bounds for these parameters, and give some examples of these new results in comparison with known conditions.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"23 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":"125019355","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
The spiked random neural network: nonlinearity, learning and approximation 尖刺随机神经网络:非线性、学习和近似
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.1998.685674
E. Gelenbe
{"title":"The spiked random neural network: nonlinearity, learning and approximation","authors":"E. Gelenbe","doi":"10.1109/CNNA.1998.685674","DOIUrl":"https://doi.org/10.1109/CNNA.1998.685674","url":null,"abstract":"We summarize the theoretical foundations of the random neural network model (RNN) and of its learning algorithm, and present a relevant bibliography of its theory and applications. Many applications have resulted from this model, including its use in still image and video compression which has achieved compression ratios of up to 500:1 for moving gray-scale images, with 30db PSNR quality levels. Another application of the RNN is to image segmentation; the recurrent feature of the network has been used to extract precise morphometric information from magnetic resonance imaging (MRI) scans of the human brain. The RNN has also been successfully applied to optimization and image texture analysis and reconstruction.","PeriodicalId":171485,"journal":{"name":"1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359)","volume":"75 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":"132347444","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: 7
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