Pub Date : 1994-12-18DOI: 10.1109/CNNA.1994.381668
T. Kozek, T. Roska
A practical cellular neural network (CNN) approximation to the Navier Stokes equation describing viscous flow of incompressible fluids is presented. The implementation of the CNN templates based on a finite difference discretization scheme, including the double time-scale CNN dynamics and the treatment of various types of boundary conditions are explained. The operation of the continuous time model is demonstrated through several examples.<>
{"title":"A double time-scale CNN for solving 2-D Navier-Stokes equations","authors":"T. Kozek, T. Roska","doi":"10.1109/CNNA.1994.381668","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381668","url":null,"abstract":"A practical cellular neural network (CNN) approximation to the Navier Stokes equation describing viscous flow of incompressible fluids is presented. The implementation of the CNN templates based on a finite difference discretization scheme, including the double time-scale CNN dynamics and the treatment of various types of boundary conditions are explained. The operation of the continuous time model is demonstrated through several examples.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132138470","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381679
Hubert Harrer, P. Venetianer, J. Nossek, T. Roska, L. O. Chua
The paper gives two examples, where an analog input image is preprocessed by a sequence of templates, i.e. by analogic CNN algorithms running on the CNN Universal Machine. The examples are: the extraction of horizontal screws with arbitrary length and the classification of screws according to their size.<>
{"title":"Some examples of preprocessing analog images with discrete-time cellular neural networks","authors":"Hubert Harrer, P. Venetianer, J. Nossek, T. Roska, L. O. Chua","doi":"10.1109/CNNA.1994.381679","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381679","url":null,"abstract":"The paper gives two examples, where an analog input image is preprocessed by a sequence of templates, i.e. by analogic CNN algorithms running on the CNN Universal Machine. The examples are: the extraction of horizontal screws with arbitrary length and the classification of screws according to their size.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133247891","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381683
F. Werblin, A. Jacobs
The vertebrate retina performs a number of highly complex transformations in space and time. Because we have not had adequate tools for analyzing these functions, little is presently known about the mechanisms underlying these transformations. CNN provides, for the first time, an analytical framework within which these transformations can be predicted, measured and analyzed. While conventional analyses have relied on studies of only single cells CNN allows us to think about, manipulate generate and study patterns of activity involving large populations of cells. Thus, CNN promises to unravel some of the important mechanisms by which the retina abstracts and encodes the visual message in space and time.<>
{"title":"Using CNN to unravel space-time processing in the vertebrate retina","authors":"F. Werblin, A. Jacobs","doi":"10.1109/CNNA.1994.381683","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381683","url":null,"abstract":"The vertebrate retina performs a number of highly complex transformations in space and time. Because we have not had adequate tools for analyzing these functions, little is presently known about the mechanisms underlying these transformations. CNN provides, for the first time, an analytical framework within which these transformations can be predicted, measured and analyzed. While conventional analyses have relied on studies of only single cells CNN allows us to think about, manipulate generate and study patterns of activity involving large populations of cells. Thus, CNN promises to unravel some of the important mechanisms by which the retina abstracts and encodes the visual message in space and time.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115558396","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381704
A. Paasio, A. Dawidziuk, K. Halonen, V. Porra
Current mode CNN with adjustable weights is discussed. Two main possible solutions are considered: continuous and discrete control. The solutions are compared on very general level and the discrete control is taken into detailed investigation. A test chip has been designed. Simulation and measurement results are reported.<>
{"title":"Digitally controllable weights in current mode cellular neural networks","authors":"A. Paasio, A. Dawidziuk, K. Halonen, V. Porra","doi":"10.1109/CNNA.1994.381704","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381704","url":null,"abstract":"Current mode CNN with adjustable weights is discussed. Two main possible solutions are considered: continuous and discrete control. The solutions are compared on very general level and the discrete control is taken into detailed investigation. A test chip has been designed. Simulation and measurement results are reported.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130574639","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381693
I. Fajfar, F. Bratkovic
Many cellular neural network design methods result in a set of linear inequalities, which they attempt to solve by various methods. In the paper we first point out the importance of the problem for the CNN design, and then expand the statistical design method proposed by R.K. Brayton, G.D. Hachtel, and S.W. Director (1978), applying it to cellular neural networks. Instead of original assumption of constant variances of the statistical parameter distributions, we take variances to be linearly dependent on parameter nominal values, which leads us to construct an iterative process with very fast convergence. A design example of winner-take-all cellular neural network is given, showing that with our improvement one can reliably implement the network of up to 50 cells as opposed to 10 cell CNN obtained by the original method.<>
{"title":"Statistical design using variable parameter variances and application to cellular neural networks","authors":"I. Fajfar, F. Bratkovic","doi":"10.1109/CNNA.1994.381693","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381693","url":null,"abstract":"Many cellular neural network design methods result in a set of linear inequalities, which they attempt to solve by various methods. In the paper we first point out the importance of the problem for the CNN design, and then expand the statistical design method proposed by R.K. Brayton, G.D. Hachtel, and S.W. Director (1978), applying it to cellular neural networks. Instead of original assumption of constant variances of the statistical parameter distributions, we take variances to be linearly dependent on parameter nominal values, which leads us to construct an iterative process with very fast convergence. A design example of winner-take-all cellular neural network is given, showing that with our improvement one can reliably implement the network of up to 50 cells as opposed to 10 cell CNN obtained by the original method.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"54 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130707410","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381656
S. Jankowski, A. Londei, C. Mazur, A. Lozowski
Complex pattern formation in two-dimensional cellular network of chaotic oscillators is presented in the paper. The patterns are related to unstable periodic orbits of the network chaotic dynamics and may be formed in the synchronization process obtained by means of chaos suppression. This effect can be considered as transition from turbulent phase to partially synchronized phase in the network.<>
{"title":"Synchronization phenomena in 2D chaotic CNN","authors":"S. Jankowski, A. Londei, C. Mazur, A. Lozowski","doi":"10.1109/CNNA.1994.381656","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381656","url":null,"abstract":"Complex pattern formation in two-dimensional cellular network of chaotic oscillators is presented in the paper. The patterns are related to unstable periodic orbits of the network chaotic dynamics and may be formed in the synchronization process obtained by means of chaos suppression. This effect can be considered as transition from turbulent phase to partially synchronized phase in the network.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130399726","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381671
P. L. Venetianer, P. Szolgay, K. R. Crounse, T. Roska, L. Chua
This paper demonstrates how certain logic and combinatorial tasks can be solved using CNNs. The most important application generalizes a shortest path algorithm to design the layout of printed circuit boards. Besides, it is shown how cellular automata can be simulated on CNN, and tasks, such as sorting, parity analysis, histogram calculation of black-and-white images, and computing minimum Hamming distance are also solved.<>
{"title":"Analog combinatorics and cellular automata-key algorithms and layout design","authors":"P. L. Venetianer, P. Szolgay, K. R. Crounse, T. Roska, L. Chua","doi":"10.1109/CNNA.1994.381671","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381671","url":null,"abstract":"This paper demonstrates how certain logic and combinatorial tasks can be solved using CNNs. The most important application generalizes a shortest path algorithm to design the layout of printed circuit boards. Besides, it is shown how cellular automata can be simulated on CNN, and tasks, such as sorting, parity analysis, histogram calculation of black-and-white images, and computing minimum Hamming distance are also solved.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130263358","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381654
A. Piovaccari, G. Setti
The design of a new CMOS building block to be used for analogically programming the control and the feedback operators of cellular neural networks is reported. The circuit was used for a repetitive programming procedure for motion detection in a 9000 transistors 7/spl times/7 CNN.<>
{"title":"A versatile CMOS building block for fully analogically-programmable VLSI cellular neural networks","authors":"A. Piovaccari, G. Setti","doi":"10.1109/CNNA.1994.381654","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381654","url":null,"abstract":"The design of a new CMOS building block to be used for analogically programming the control and the feedback operators of cellular neural networks is reported. The circuit was used for a repetitive programming procedure for motion detection in a 9000 transistors 7/spl times/7 CNN.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114183049","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381709
K. Lotz, Zoltán Vidnyánszky, T. Roskar, Joos P. Vandewalle, J. Hámori, A. Jacobs, F. Werblin
In this paper we show cellular neural network (CNN) models of some basic types of cells characterised by diverse spiking patterns. After showing some preliminary models (ion channels, neurons), CNN models of the action potential generation are given followed by an analysis of the rate coding capabilities of the models. Furthermore, CNN models of neurons with diverse intrinsic firing patterns are presented followed by some conclusions.<>
{"title":"Some cortical spiking neuron models using CNN","authors":"K. Lotz, Zoltán Vidnyánszky, T. Roskar, Joos P. Vandewalle, J. Hámori, A. Jacobs, F. Werblin","doi":"10.1109/CNNA.1994.381709","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381709","url":null,"abstract":"In this paper we show cellular neural network (CNN) models of some basic types of cells characterised by diverse spiking patterns. After showing some preliminary models (ion channels, neurons), CNN models of the action potential generation are given followed by an analysis of the rate coding capabilities of the models. Furthermore, CNN models of neurons with diverse intrinsic firing patterns are presented followed by some conclusions.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133451301","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 : 1994-12-18DOI: 10.1109/CNNA.1994.381639
R. Domínguez-Castro, S. Espejo, Á. Rodríguez-Vázquez, I. Garcia-Vargas, J. Ramos, R. Carmona
SIRENA is a general simulation environment for artificial neural networks, with emphasis towards CNNs. A special interest has been placed in allowing the simulation and modelling of the non-ideal effects expected from VLSI implementations. SIRENA allows the simulation of CNNs in greater detail than conventional CNN simulators, and much more efficiently than SPICE-type electrical simulators.<>
{"title":"SIRENA: a simulation environment for CNNs","authors":"R. Domínguez-Castro, S. Espejo, Á. Rodríguez-Vázquez, I. Garcia-Vargas, J. Ramos, R. Carmona","doi":"10.1109/CNNA.1994.381639","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381639","url":null,"abstract":"SIRENA is a general simulation environment for artificial neural networks, with emphasis towards CNNs. A special interest has been placed in allowing the simulation and modelling of the non-ideal effects expected from VLSI implementations. SIRENA allows the simulation of CNNs in greater detail than conventional CNN simulators, and much more efficiently than SPICE-type electrical simulators.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122848494","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：