Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207522
J. L. Huertas, A. Rueda
Addresses the problem of testing an ACNN by postulating the need of including some extra hardware to rend feasible a post-fabrication test. The work presented deals with a test methodology based on adding some extra circuitry to every cell of a regular ACNN. This methodology is just an initial proposal for taking an advantage of the network regularity to perform a global test that can be externally interpreted and, hence, has potential application for reconfiguring the network.<>
{"title":"Testability issues in analog cellular neural networks","authors":"J. L. Huertas, A. Rueda","doi":"10.1109/CNNA.1990.207522","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207522","url":null,"abstract":"Addresses the problem of testing an ACNN by postulating the need of including some extra hardware to rend feasible a post-fabrication test. The work presented deals with a test methodology based on adding some extra circuitry to every cell of a regular ACNN. This methodology is just an initial proposal for taking an advantage of the network regularity to perform a global test that can be externally interpreted and, hence, has potential application for reconfiguring the network.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132363852","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207527
J. E. Varrientos, J. Ramírez-Angulo, E. Sánchez-Sinencio
A current-mode CMOS circuit implementation of a cellular neural network is discussed. The implementation mimics classical cellular automata and has been designed for image processing. Signals are processed in current mode using simple current mirrors, inverters, and sources. Simulations for networks constructed have shown effectiveness in edge detection and noise removal.<>
{"title":"Cellular neural network implementations: a current mode approach","authors":"J. E. Varrientos, J. Ramírez-Angulo, E. Sánchez-Sinencio","doi":"10.1109/CNNA.1990.207527","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207527","url":null,"abstract":"A current-mode CMOS circuit implementation of a cellular neural network is discussed. The implementation mimics classical cellular automata and has been designed for image processing. Signals are processed in current mode using simple current mirrors, inverters, and sources. Simulations for networks constructed have shown effectiveness in edge detection and noise removal.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117043381","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207526
K. Halonen, V. Porra, T. Roska, L. Chua
A new integrated circuit cellular neural network implementation having digitally or continuously selectable template coefficients is presented. Local logic and memory is added into each cell providing a simple dual computing structure (analog and digital). The variable-gain operational transconductance amplifier (OTA) is used as voltage controlled current sources to program the weighting factors of the template elements. A 4-by-4 CNN circuit is realized using the 2 mu m analog CMOS-process. The circuit with different template configurations has been simulated with HSPIC.<>
{"title":"VLSI implementation of a reconfigurable cellular neural network containing local logic (CNNL)","authors":"K. Halonen, V. Porra, T. Roska, L. Chua","doi":"10.1109/CNNA.1990.207526","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207526","url":null,"abstract":"A new integrated circuit cellular neural network implementation having digitally or continuously selectable template coefficients is presented. Local logic and memory is added into each cell providing a simple dual computing structure (analog and digital). The variable-gain operational transconductance amplifier (OTA) is used as voltage controlled current sources to program the weighting factors of the template elements. A 4-by-4 CNN circuit is realized using the 2 mu m analog CMOS-process. The circuit with different template configurations has been simulated with HSPIC.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122439984","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207505
G. Wunsch, W. Mathis
The theory of linear systems is a black box concept where the boxes are described by means of transfer functions. By use of the state-space concept the system theoretical approach is applicable to nonlinear input-output systems, too. Neural networks, which are highly structured systems, are built up of interconnected identical nonlinear components of a very simple type. The availability of VLSI technology has had a great impact on the development of these electronic cellular structures. The classical theory of time systems is not well-adapted for analysing such 'cellular systems' varying in space and time. The authors present a conception of space-time systems developed by Wunsch (1975, 1977), and show that this concept is very suitable for a system-theoretical description of the class of cellular neural networks discovered by L.O. Chua and L. Yang (1988).<>
{"title":"Toward a theory of cellular systems","authors":"G. Wunsch, W. Mathis","doi":"10.1109/CNNA.1990.207505","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207505","url":null,"abstract":"The theory of linear systems is a black box concept where the boxes are described by means of transfer functions. By use of the state-space concept the system theoretical approach is applicable to nonlinear input-output systems, too. Neural networks, which are highly structured systems, are built up of interconnected identical nonlinear components of a very simple type. The availability of VLSI technology has had a great impact on the development of these electronic cellular structures. The classical theory of time systems is not well-adapted for analysing such 'cellular systems' varying in space and time. The authors present a conception of space-time systems developed by Wunsch (1975, 1977), and show that this concept is very suitable for a system-theoretical description of the class of cellular neural networks discovered by L.O. Chua and L. Yang (1988).<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127092888","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207512
T. Matsumoto, T. Yokohama, H. Suzuki, Ryo Furukawa, A. Oshimoto, T. Shimmi, Y. Matsushita, T. Seo, Leon O. Chua
Cellular neural net templates for image processing are described. The functions performed by the templates are connected component detection, hole-filling, image thinning, shadow detection and Japanese character recognition.<>
{"title":"Several image processing examples by CNN","authors":"T. Matsumoto, T. Yokohama, H. Suzuki, Ryo Furukawa, A. Oshimoto, T. Shimmi, Y. Matsushita, T. Seo, Leon O. Chua","doi":"10.1109/CNNA.1990.207512","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207512","url":null,"abstract":"Cellular neural net templates for image processing are described. The functions performed by the templates are connected component detection, hole-filling, image thinning, shadow detection and Japanese character recognition.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125843780","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207530
M. Johnson, M. Brown, N. Allinson
Presents a technique that may be used for clustering in a very high dimensionality pattern space. The desirability of a self organising algorithm which can learn an internal representation for use in a pattern recogniser is shown. Using such an algorithm, subspace methods are brought together with an associative memory to form a pattern recogniser which employs unsupervised learning. The representation used for signal pattern clusters is based on topologically ordered units, each of which can label a complex area of pattern space. An adaption algorithm is given and shown to be insensitive to the variation in vector magnitudes which is found within a typical training set. A number of examples are given showing clustering of real grey scale, visual data and the reconstruction of exemplars using adaptive feedback. The application of this to vector quantisation and noise removal is demonstrated.<>
{"title":"Multidimensional self organisation","authors":"M. Johnson, M. Brown, N. Allinson","doi":"10.1109/CNNA.1990.207530","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207530","url":null,"abstract":"Presents a technique that may be used for clustering in a very high dimensionality pattern space. The desirability of a self organising algorithm which can learn an internal representation for use in a pattern recogniser is shown. Using such an algorithm, subspace methods are brought together with an associative memory to form a pattern recogniser which employs unsupervised learning. The representation used for signal pattern clusters is based on topologically ordered units, each of which can label a complex area of pattern space. An adaption algorithm is given and shown to be insensitive to the variation in vector magnitudes which is found within a typical training set. A number of examples are given showing clustering of real grey scale, visual data and the reconstruction of exemplars using adaptive feedback. The application of this to vector quantisation and noise removal is demonstrated.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116631462","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207509
F. Zou, S. Schwarz, J. Nossek
A learning algorithm for cellular neural networks (CNN) is proposed. The cloning templates can be obtained by using this algorithm, which is based on the relaxation method for solving sets of linear inequalities. The symmetry of templates can be forced through additional equality constraints. Simulation examples show that some useful templates with the smallest neighborhood N/sub 1/(i, j) are generated by the application of the training rule.<>
{"title":"Cellular neural network design using a learning algorithm","authors":"F. Zou, S. Schwarz, J. Nossek","doi":"10.1109/CNNA.1990.207509","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207509","url":null,"abstract":"A learning algorithm for cellular neural networks (CNN) is proposed. The cloning templates can be obtained by using this algorithm, which is based on the relaxation method for solving sets of linear inequalities. The symmetry of templates can be forced through additional equality constraints. Simulation examples show that some useful templates with the smallest neighborhood N/sub 1/(i, j) are generated by the application of the training rule.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114615541","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207510
K. Slot
Issues involved in cellular neural net design are discussed, and recommendations are made for parameter choice. Inherent errors of detection are pointed out and a method for their reduction is proposed. Complex signal processing in the net from the point of view of error occurrences is also discussed. A simple cell architecture is introduced, and its modification, appropriate for complex signal processing, is presented.<>
{"title":"Determination of cellular neural networks parameters for feature detection of two-dimensional images","authors":"K. Slot","doi":"10.1109/CNNA.1990.207510","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207510","url":null,"abstract":"Issues involved in cellular neural net design are discussed, and recommendations are made for parameter choice. Inherent errors of detection are pointed out and a method for their reduction is proposed. Complex signal processing in the net from the point of view of error occurrences is also discussed. A simple cell architecture is introduced, and its modification, appropriate for complex signal processing, is presented.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122126669","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207514
G. Seiler
This report presents a completely cellular neural network-based system architecture for small object counting, where the center positions of small patterns of known shape, size and orientation are located in an input image, in order to be finally counted. The system consists of three cascaded image processing stages: preprocessing performs noise filtering and contrast enhancement, pattern matching approximately locates object positions, and isolating ensures uniqueness of perceived object center locations. Some templates for isolating are presented; their stability is proven.<>
{"title":"Small object counting with cellular neural networks","authors":"G. Seiler","doi":"10.1109/CNNA.1990.207514","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207514","url":null,"abstract":"This report presents a completely cellular neural network-based system architecture for small object counting, where the center positions of small patterns of known shape, size and orientation are located in an input image, in order to be finally counted. The system consists of three cascaded image processing stages: preprocessing performs noise filtering and contrast enhancement, pattern matching approximately locates object positions, and isolating ensures uniqueness of perceived object center locations. Some templates for isolating are presented; their stability is proven.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132755983","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}
Pub Date : 1990-12-16DOI: 10.1109/CNNA.1990.207513
P. Kaluzny, S. Kukliński
Summary form only given. Concerns the use of stable analog cellular neural networks (CNN) for image processing. CNN architecture can be treated as a space-invariant iterative nonlinear filter. The authors compare CNNs and other techniques in image processing. The analysis is performed for two kinds of tasks for which nonlinear filters are commonly used: noise suppression and edge detection. Two synthesized test images, 64*64 pixels each, are used in experiments. One consists of solid blocks of different shapes and the other contains thin lines and sharp corners. The images are added with zero-mean Gaussian noise and impulsive noise. The efficiency of noise removal is examined. The limiter type M filter, a type of median filter, is considered. Edge detection by various filters and operators is compared.<>
{"title":"Properties of cellular neural networks in selected image processing applications","authors":"P. Kaluzny, S. Kukliński","doi":"10.1109/CNNA.1990.207513","DOIUrl":"https://doi.org/10.1109/CNNA.1990.207513","url":null,"abstract":"Summary form only given. Concerns the use of stable analog cellular neural networks (CNN) for image processing. CNN architecture can be treated as a space-invariant iterative nonlinear filter. The authors compare CNNs and other techniques in image processing. The analysis is performed for two kinds of tasks for which nonlinear filters are commonly used: noise suppression and edge detection. Two synthesized test images, 64*64 pixels each, are used in experiments. One consists of solid blocks of different shapes and the other contains thin lines and sharp corners. The images are added with zero-mean Gaussian noise and impulsive noise. The efficiency of noise removal is examined. The limiter type M filter, a type of median filter, is considered. Edge detection by various filters and operators is compared.<<ETX>>","PeriodicalId":142909,"journal":{"name":"IEEE International Workshop on Cellular Neural Networks and their Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133561672","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：