发布求助
文献互助 智能选刊 最新文献

2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)最新文献

筛选
英文 中文
Leaning theory of Cellular Neural Networks based on covariance structural analysis 基于协方差结构分析的细胞神经网络学习理论
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430326
M. Tanaka, H. Aomori, Y. Nishio, K. Oshima, M. Hasler
{"title":"Leaning theory of Cellular Neural Networks based on covariance structural analysis","authors":"M. Tanaka, H. Aomori, Y. Nishio, K. Oshima, M. Hasler","doi":"10.1109/CNNA.2010.5430326","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430326","url":null,"abstract":"This paper describes a learning theory of the CNN based on the covariance structure analysis using new numerical integral methods. In general, a Cellular Neural Network (CNN) is defined as a local connected circuit which has continuous state variables x ¿Rn. The importance is in that the piece-wise linear function of the CNN has a linear region |x| ¿ 1 for x ¿ x because the learning method can be constructed only in linear state and measurement equations, and because the linear region can be quantized from the continuous variable x to the multilevel quantized variable f(x) by each 1-bit ¿¿ modulator which is corresponding to a spiking neuron model. That is, our purpose is to determine the weight parameters ¿ in the connection matrices A, B, C, D, T and e by the machine learning method for equilibrium points of the CNN states equation x = 0. The covariance structure for the equilibrium point to the linear region will be constructed based on extended Chua's CNN theorem to have symmetric edges for aij = aji and asymmetric one-way edge aij ¿ 0 for aji = 0 for A-matrix A = [aij].","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116506544","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
VLSI circuits for multiplexed Star CNNs 用于多路星型cnn的VLSI电路
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430272
F. Sargeni, V. Bonaiuto
{"title":"VLSI circuits for multiplexed Star CNNs","authors":"F. Sargeni, V. Bonaiuto","doi":"10.1109/CNNA.2010.5430272","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430272","url":null,"abstract":"The design of circuits to implement complex systems as Star Cellular Neural Networks requires custom VLSI design with high features and performances. The paper deals with the VLSI design of circuits in current mode properly developed to multiplexed implementation of a Star CNNs.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"515 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116216087","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
Fast computation of particle filters on processor arrays 处理器阵列上粒子滤波的快速计算
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430293
A. Horváth, M. Rásonyi
{"title":"Fast computation of particle filters on processor arrays","authors":"A. Horváth, M. Rásonyi","doi":"10.1109/CNNA.2010.5430293","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430293","url":null,"abstract":"We have developed a new variant of the particle filter algorithm for estimating a signal from noisy observations. It suits ideally implementation on a cellular processor array. The error of the new algorithm is essentially the same as that of the old one but it runs much faster, especially when there is a large number of particles to be simulated.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123323212","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
Digital processor array implementation aspects of a 3D multi-layer vision architecture 数字处理器阵列方面实现了一种三维多层视觉架构
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430274
P. Foldesy, R. Carmona-Galán, Á. Zarándy, C. Rekeczky, Á. Rodríguez-Vázquez, T. Roska
{"title":"Digital processor array implementation aspects of a 3D multi-layer vision architecture","authors":"P. Foldesy, R. Carmona-Galán, Á. Zarándy, C. Rekeczky, Á. Rodríguez-Vázquez, T. Roska","doi":"10.1109/CNNA.2010.5430274","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430274","url":null,"abstract":"Technological aspects of the 3D integration of a multilayer combined mixed-signal and digital sensor-processor array chip is described. The 3D integration raises the question of signal routing, power distribution, and heat dissipation, which aspects are considered systematically in the digital processor array layer as part of the multi layer structure. We have developed a linear programming based evaluation system to identify the proper architecture and its parameters.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123803008","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
Arithmetic operations within memristor-based analog memory 基于忆阻器的模拟存储器中的算术运算
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430319
M. Laiho, E. Lehtonen
{"title":"Arithmetic operations within memristor-based analog memory","authors":"M. Laiho, E. Lehtonen","doi":"10.1109/CNNA.2010.5430319","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430319","url":null,"abstract":"This paper describes how memristors could be used as an analog memory and computing elements. The key idea is to apply comparison and programming phases cyclically so that the memristor can be programmed to a given conductance level at a fixed voltage. It is further described how the cyclical programming could be used in computing. A configuration needed to copy the sum of conductances of two memristors into a third one is described. It is further shown how the devices could be configured so that addition and subtraction of positive and negative analog conductances could be performed. The presented memory structure requires a memristor model with a nonlinear programming sensitivity (programming threshold) for proper programming selectivity. A model of such a memristor is shown and key simulations are presented.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128650716","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: 33
Analysis of signal propagation in 1-D CNNs with the antisymmetric template 基于反对称模板的一维cnn信号传播分析
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430264
N. Takahashi, T. Nishi, H. Hara
{"title":"Analysis of signal propagation in 1-D CNNs with the antisymmetric template","authors":"N. Takahashi, T. Nishi, H. Hara","doi":"10.1109/CNNA.2010.5430264","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430264","url":null,"abstract":"This paper studies some fundamental properties on signal propagation in one-dimensional cellular neural networks with the antisymmetric template under the assumption that the initial output has only one connected component. A new sufficient condition for the component to propagate without attenuation is derived through theoretical analysis. It is also proved that under the same condition the final output is a black-and-white image having only one black at the right-most pixel, which means that the network can perform connected component detection when the input image has only one connected component.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128819947","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
Designing efficient CNN algorithms for the Bionic Eyeglass by combining manual and automatic techniques 结合人工与自动技术，设计高效的仿生眼镜CNN算法
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430297
G. E. Pazienza, K. Karacs, E.A. Horvafh, G. Mate
{"title":"Designing efficient CNN algorithms for the Bionic Eyeglass by combining manual and automatic techniques","authors":"G. E. Pazienza, K. Karacs, E.A. Horvafh, G. Mate","doi":"10.1109/CNNA.2010.5430297","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430297","url":null,"abstract":"Programs for the CNN-UM can be designed either manually or automatically. These two approaches have complementary advantages and disadvantages, and hence neither of them can be considered as the better choice. In this paper, we find empirical evidence that these two techniques can be combined in order to obtain more effective and efficient algorithms.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125433673","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
Binary synchronization of chaos in hybrid cellular automata for low complexity image compression and transmission 混合元胞自动机中混沌二值同步的低复杂度图像压缩与传输
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430253
R. Dogaru, I. Dogaru, Hyongsuk Kim, Sungsik Shin, O. Gwun
{"title":"Binary synchronization of chaos in hybrid cellular automata for low complexity image compression and transmission","authors":"R. Dogaru, I. Dogaru, Hyongsuk Kim, Sungsik Shin, O. Gwun","doi":"10.1109/CNNA.2010.5430253","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430253","url":null,"abstract":"This paper exploits an interesting property of a certain type of elementary cellular automata, namely hybrid cellular automata (HCA) defined by rule 101 and its negate. Such HCA may be easily implemented on any CNN platform, and has some interesting properties. It provides a chaotic counting automaton instead of the traditional raster scan counter addressing the multiple sensing elements. Replacing raster scan with chaotic scan provided by the HCA allows implementation of both progressive image compression and spread spectrum transmission with a very low complexity of the transmitting sensor. The clear advantages of our system in terms of implementation complexity, makes it a valuable candidate for low power sensor networks applications.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114680122","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
Bio-inspired looming object detector algorithm on the Eye-RIS focal plane-processor system 基于Eye-RIS焦平面处理器系统的仿生若隐若现目标检测算法
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430290
T. Fulop, Á. Zarándy
{"title":"Bio-inspired looming object detector algorithm on the Eye-RIS focal plane-processor system","authors":"T. Fulop, Á. Zarándy","doi":"10.1109/CNNA.2010.5430290","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430290","url":null,"abstract":"Bio-inspired approaching object detection algorithms have been proposed since Shea, Rowell and Williams found the approaching object detection retinal circuitry of Locusta Migratoria in 1974. Recently, Botond Roska's group identified a looming sensitive circuit in mammalian retina. The newly discovered retina circuit is based on local interaction, therefore, this new discovery enables the development of efficient looming object detection algorithms for topographic kiloprocessor chips. This paper presents the bases of the new model and shows the implementation on Eye-RIS sensor-processor device.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114898071","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
Image processing application using CNN with dynamic template 图像处理应用采用CNN带动态模板
2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010) Pub Date : 2010-03-29 DOI: 10.1109/CNNA.2010.5430330
M. Kawahara, T. Inoue, Y. Nishio
{"title":"Image processing application using CNN with dynamic template","authors":"M. Kawahara, T. Inoue, Y. Nishio","doi":"10.1109/CNNA.2010.5430330","DOIUrl":"https://doi.org/10.1109/CNNA.2010.5430330","url":null,"abstract":"In this research, we propose an image processing application using cellular neural networks (CNN) with dynamic template (D-CNN). In D-CNN, the wiring weights of template are dynamically changed at each update by learning. In this study, we also focus on the number of converged value. Thus, some converged values of each cell in the initial input image are changed by effect of next input image in motion picture. Although input image is only still image, we think that if multiple input images are inputted to the D-CNN as motion picture, converged values of each cell are continued to changed. We investigate the converged value by changing input image. The results indicate that D-CNN can be applied to the region segregated processing for the motion picture.","PeriodicalId":336891,"journal":{"name":"2010 12th International Workshop on Cellular Nanoscale Networks and their Applications (CNNA 2010)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133182928","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
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