Pub Date : 1994-12-18DOI: 10.1109/CNNA.1994.381685
M. Joy, V. Tavsanoglu
In this paper we show that feedback matrices of ring CNNs are block circulants; as special cases, for example, feedback matrices of one-dimensional ring CNNs are circulant matrices. Circulants and their close relations the block circulants possess many pleasant properties which allow one to describe their spectrum completely. After deriving the spectrum of the feedback operator we present the main theorem of this paper which gives a parameter range for which convergence of the CNN dynamical system is assured.<>
{"title":"Circulant matrices and the stability theory of CNNs","authors":"M. Joy, V. Tavsanoglu","doi":"10.1109/CNNA.1994.381685","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381685","url":null,"abstract":"In this paper we show that feedback matrices of ring CNNs are block circulants; as special cases, for example, feedback matrices of one-dimensional ring CNNs are circulant matrices. Circulants and their close relations the block circulants possess many pleasant properties which allow one to describe their spectrum completely. After deriving the spectrum of the feedback operator we present the main theorem of this paper which gives a parameter range for which convergence of the CNN dynamical system is assured.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"74 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":"124196468","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.1994.381659
P. Szolgay, G. Voros
Cellular neural networks (CNNs) paradigm is applied in the paper to compute the transient response of mechanical vibrating systems. Based on previous theoretical results on this field we would like to show (i) how the CNN templates can be generated automatically by a subroutine from the COSMOS/M finite element analysis system; (ii) how we assign to each degree of freedom two coupled CNN layers and how the templates are derived. Some interesting examples are shown and analyzed.<>
{"title":"Transient response computation of a mechanical vibrating system using cellular neural networks","authors":"P. Szolgay, G. Voros","doi":"10.1109/CNNA.1994.381659","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381659","url":null,"abstract":"Cellular neural networks (CNNs) paradigm is applied in the paper to compute the transient response of mechanical vibrating systems. Based on previous theoretical results on this field we would like to show (i) how the CNN templates can be generated automatically by a subroutine from the COSMOS/M finite element analysis system; (ii) how we assign to each degree of freedom two coupled CNN layers and how the templates are derived. Some interesting examples are shown and analyzed.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"29 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":"123777774","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.1994.381669
P. Szolgay, A. Katona, G. Eross, A. Kiss
An experimental system was built up and tested for optical path tracking of a robot, where a 16*16 connected component detector chip with direct optical input was used. The speed of computation in the experimental architecture was analyzed.<>
{"title":"An experimental system for path tracking of a robot using a 16*16 connected component detector CNN chip with direct optical input","authors":"P. Szolgay, A. Katona, G. Eross, A. Kiss","doi":"10.1109/CNNA.1994.381669","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381669","url":null,"abstract":"An experimental system was built up and tested for optical path tracking of a robot, where a 16*16 connected component detector chip with direct optical input was used. The speed of computation in the experimental architecture was analyzed.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"35 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":"131949330","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.1994.381666
B. Sheu, S. Bang, W. Fang
An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks have great potential in solving many important scientific problems in signal processing and optimization by the use of predetermined templates. Hardware annealing (SaHyun Bang, 1994), which is a paralleled version of effective mean field annealing in analog networks, is a highly efficient method of finding optimal solutions for cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed hardware annealing method can be described by eigenvalues in the time varying dynamic system.<>
{"title":"Optimal solutions of selected cellular neural network applications by the hardware annealing method","authors":"B. Sheu, S. Bang, W. Fang","doi":"10.1109/CNNA.1994.381666","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381666","url":null,"abstract":"An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks have great potential in solving many important scientific problems in signal processing and optimization by the use of predetermined templates. Hardware annealing (SaHyun Bang, 1994), which is a paralleled version of effective mean field annealing in analog networks, is a highly efficient method of finding optimal solutions for cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed hardware annealing method can be described by eigenvalues in the time varying dynamic system.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"24 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":"127489365","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：