1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)最新文献_第9页

Lossless cellular neural networks 无损细胞神经网络

1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566515

A. Schlaffer, J. Nossek, M. Tanaka

{"title":"Lossless cellular neural networks","authors":"A. Schlaffer, J. Nossek, M. Tanaka","doi":"10.1109/CNNA.1996.566515","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566515","url":null,"abstract":"Since their introduction, cellular neural networks have turned out to be useful architectures for the solution of many problems, e.g. in image processing or in the simulation of partial differential equations. Therefore, there have been several attempts to introduce cell circuits suitable for large-scale integration. Up to now, all of these cells need energy and therefore power supply. Recently attempts have been made to build up circuitry able to work without an external energy supply by using the energy stored in the initial state. This principle can provide two major advantages. First, since no or at least not much energy is dissipated during computation, the circuit does not produce much heat. Therefore, there are no \"hot spots\" in integrated circuits, which limit integration density and operation speed. Furthermore, since there is no need for a power supply, the absence of voltage supply lines supports a high integration density. In this work an architecture for the realisation of a lossless CNN is proposed. Further, since standard learning algorithms turn out to fail for lossless systems, a way to amend these is introduced.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131630303","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

Cellular neural network for Markov random field image segmentation 基于细胞神经网络的马尔可夫随机场图像分割

1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566509

Tamás Szirányi, J. Zerubia, D. Geldreich, Zoltan Kato

{"title":"Cellular neural network for Markov random field image segmentation","authors":"Tamás Szirányi, J. Zerubia, D. Geldreich, Zoltan Kato","doi":"10.1109/CNNA.1996.566509","DOIUrl":"https://doi.org/10.1109/CNNA.1996.566509","url":null,"abstract":"Statistical approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. CNN is a fast parallel processor array for image processing. However, CNN is basically a deterministic analog circuit. We use the CNN-UM architecture for statistical image segmentation. With a single random in-put signal, we were able to implement a (pseudo) random field generator using one layer (one memory/cell) of the CNN. The whole algorithm needs 8 memories/cell. We can introduce this pseudo-stochastic segmentation process in the CNN structure. Considering the simple structure of the analog VLSI design, we use simple arithmetic functions (addition, multiplication) and very simple nonlinear output functions (step, jigsaw). With this architecture, a real VLSI CNN chip can execute a pseudo-stochastic relaxation algorithm of about 100 iterations in about 1 msec. In the Markov random field (MRF) theory, one important problem is parameter estimation. The random segmentation process must be preceded by the estimation of the gray-level distribution of the different classes on small image segments. This process is basically supervised. Usually the histograms of noisy images can be modelled as simple Gaussian distributions. This approach cannot be held in a CNN structure, since there should be as many additional layers as the number of classes. We should follow another way. We have developed a pixel-level distribution model.","PeriodicalId":222524,"journal":{"name":"1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132469001","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

Synchronisation phenomena in RC oscillators coupled by one nonlinear negative resistor 非线性负电阻器耦合RC振荡器中的同步现象

1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566506

N. Kawano, S. Moro, S. Mori

引用次数: 0

Optical detection of breaks and short circuits on the layouts of printed circuit boards using CNN 利用CNN对印刷电路板布局上的断路和短路进行光学检测

1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566498

P. Szolgay, K. Tomordi

引用次数: 7

Analogic algorithm for point pattern matching with application to mammogram follow-up 点模式匹配的类比算法及其在乳腺x线随访中的应用

1996 Fourth IEEE International Workshop on Cellular Neural Networks and their Applications Proceedings (CNNA-96) Pub Date : 1996-06-24 DOI: 10.1109/CNNA.1996.566496

N. Vujovic, P. Bakic, D. Brzakovic

引用次数: 4