Pub Date : 1994-12-18DOI: 10.1109/CNNA.1994.381663
Chunmei Yang, Ta-lun Yang, Kangming Zhang
The quasi-period and chaos in discrete time cellular neural networks (DTCNN) are studied in this paper. In a 2-cell autonomous DTCNN, theories for periodic and quasi-periodic motions are presented. Chaos is found in 2 and 3-cell autonomous and nonautonomous DTCNNs. The structures of the strange attractors are shown. The bifurcation diagrams are used to show the transition procedures of the DTCNNs from the periodic motion to chaos. A strange attractor with 2 separated branches is also found in a 3-cell DTCNN.<>
{"title":"Chaos in the discrete time cellular neural networks","authors":"Chunmei Yang, Ta-lun Yang, Kangming Zhang","doi":"10.1109/CNNA.1994.381663","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381663","url":null,"abstract":"The quasi-period and chaos in discrete time cellular neural networks (DTCNN) are studied in this paper. In a 2-cell autonomous DTCNN, theories for periodic and quasi-periodic motions are presented. Chaos is found in 2 and 3-cell autonomous and nonautonomous DTCNNs. The structures of the strange attractors are shown. The bifurcation diagrams are used to show the transition procedures of the DTCNNs from the periodic motion to chaos. A strange attractor with 2 separated branches is also found in a 3-cell DTCNN.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"48 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":"132257131","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.1994.381636
M. Csapodi, L. Nemes, G. Tóth, T. Roska, A. Radványi
In this paper three interesting analogic CNN algorithms are presented for three tasks. The first task is to move a given 2D object along a prescribed path, the second task is the approximation of 3D surfaces by various interpolation and approximation methods and the third task is a specific detection problem. In this detection problem our task is to detect a "door-in-a-floor" by finding the handle and possibly the place of a text or symbol on the door. The solution methods of the tasks are summarized.<>
{"title":"Some novel analogic CNN algorithms for object rotation, 3D interpolation-approximation, and a \"door-in-a-floor\" problem","authors":"M. Csapodi, L. Nemes, G. Tóth, T. Roska, A. Radványi","doi":"10.1109/CNNA.1994.381636","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381636","url":null,"abstract":"In this paper three interesting analogic CNN algorithms are presented for three tasks. The first task is to move a given 2D object along a prescribed path, the second task is the approximation of 3D surfaces by various interpolation and approximation methods and the third task is a specific detection problem. In this detection problem our task is to detect a \"door-in-a-floor\" by finding the handle and possibly the place of a text or symbol on the door. The solution methods of the tasks are summarized.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"142 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":"126954978","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.1994.381692
N. Aizenberg, I. Aizenberg
We consider fast convergence learning algorithms for multi-valued and universal binary neurons. These neurons are suggested to be used for design of neural networks based on CNN paradigm. On the basis of such networks we offer to solve some problems of image processing. For instance, high efficient method for contours detection obtained by learning algorithm described in the paper is presented. Also solution of the XOR-problem on the single neuron is described.<>
{"title":"CNN-like networks based on multi-valued and universal binary neurons: learning and application to image processing","authors":"N. Aizenberg, I. Aizenberg","doi":"10.1109/CNNA.1994.381692","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381692","url":null,"abstract":"We consider fast convergence learning algorithms for multi-valued and universal binary neurons. These neurons are suggested to be used for design of neural networks based on CNN paradigm. On the basis of such networks we offer to solve some problems of image processing. For instance, high efficient method for contours detection obtained by learning algorithm described in the paper is presented. Also solution of the XOR-problem on the single neuron is described.<<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":"123472505","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.1994.381706
J. M. Cruz, L. Chua, T. Roska
In this paper we report on a fast, complex and efficient implementation of the Cellular Neural Network Universal Machine as an IC chip. The chip has continuous time analog dynamics, and has been designed to process 500,000 image frames per second.<>
{"title":"A fast, complex and efficient test implementation of the CNN Universal Machine","authors":"J. M. Cruz, L. Chua, T. Roska","doi":"10.1109/CNNA.1994.381706","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381706","url":null,"abstract":"In this paper we report on a fast, complex and efficient implementation of the Cellular Neural Network Universal Machine as an IC chip. The chip has continuous time analog dynamics, and has been designed to process 500,000 image frames per second.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"9 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":"114369470","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.1994.381648
A. Sani, S. Graffi, G. Masetti, G. Setti
The design of a CMOS cellular neural network able to correctly operate in a wide range of supply-voltages is reported. The electrical characteristics of the basic building blocks are analysed and discussed. Additionally, some performances of a 10/spl times/10 CNN are reported.<>
{"title":"Design of CMOS cellular neural networks operating at several supply voltages","authors":"A. Sani, S. Graffi, G. Masetti, G. Setti","doi":"10.1109/CNNA.1994.381648","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381648","url":null,"abstract":"The design of a CMOS cellular neural network able to correctly operate in a wide range of supply-voltages is reported. The electrical characteristics of the basic building blocks are analysed and discussed. Additionally, some performances of a 10/spl times/10 CNN are reported.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"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":"114536987","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.1994.381632
P. Arena, S. Baglio, L. Fortuna, G. Manganaro
A method to filter 2D NMR spectra against uncertainties arising from experiments and data acquisition machinery is proposed. This is achieved by using a cellular neural network. The method introduced is explained and is applied to filtering of a real 2D NMR spectrum of a protein.<>
{"title":"CNN processing for NMR spectra","authors":"P. Arena, S. Baglio, L. Fortuna, G. Manganaro","doi":"10.1109/CNNA.1994.381632","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381632","url":null,"abstract":"A method to filter 2D NMR spectra against uncertainties arising from experiments and data acquisition machinery is proposed. This is achieved by using a cellular neural network. The method introduced is explained and is applied to filtering of a real 2D NMR spectrum of a protein.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"94 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":"115649268","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.1994.381710
T. Roska
In this paper first we classify the analogic CNN algorithms; instructions, subroutines, and programs. The complexity of analogic algorithms is defined based on Chaitin's definition of algorithmic computational complexity for digital algorithms. The algorithmic design and implementation phases are analyzed. It is shown how the analogic CNN algorithms are related to the living sensory systems.<>
{"title":"Analogic algorithms running on the CNN Universal Machine","authors":"T. Roska","doi":"10.1109/CNNA.1994.381710","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381710","url":null,"abstract":"In this paper first we classify the analogic CNN algorithms; instructions, subroutines, and programs. The complexity of analogic algorithms is defined based on Chaitin's definition of algorithmic computational complexity for digital algorithms. The algorithmic design and implementation phases are analyzed. It is shown how the analogic CNN algorithms are related to the living sensory systems.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"58 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":"115162197","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.1994.381670
Á. Zarándy, T. Roska, GY Liszka, J. Hegyesi, L. Kék, Csaba Rekeczky
CNN analogic algorithms were developed for detecting the features of breast cancer on X-ray mammograms.<>
CNN模拟算法被开发用于检测x射线乳房x光片上的乳腺癌特征
{"title":"Design of analogic CNN algorithms for mammogram analysis","authors":"Á. Zarándy, T. Roska, GY Liszka, J. Hegyesi, L. Kék, Csaba Rekeczky","doi":"10.1109/CNNA.1994.381670","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381670","url":null,"abstract":"CNN analogic algorithms were developed for detecting the features of breast cancer on X-ray mammograms.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"23 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":"117013316","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.1994.381702
M.-D. Doan, M. Glesner, R. Chakrabaty, M. Heidenreich, S. Cheung
A a digital cellular neural network (DCNN) based on the SIMD-architecture is presented. The network is optimized for image processing applications. Due to the massive parallel architecture of the global structure and due to the local parallel operating blocks of the cells, high calculating speed can be obtained. Processing of images with sizes up to 100/spl times/100 pixels in realtime is principally possible. In order to process large images, which are much greater than the physical network, virtual processing is needed, and supported by the hardware. As prototype, a cascadable net of 2/spl times/2 cells is implemented on a chip using the 1.0 /spl mu/ process of ES2.<>
{"title":"Realisation of a digital cellular neural network for image processing","authors":"M.-D. Doan, M. Glesner, R. Chakrabaty, M. Heidenreich, S. Cheung","doi":"10.1109/CNNA.1994.381702","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381702","url":null,"abstract":"A a digital cellular neural network (DCNN) based on the SIMD-architecture is presented. The network is optimized for image processing applications. Due to the massive parallel architecture of the global structure and due to the local parallel operating blocks of the cells, high calculating speed can be obtained. Processing of images with sizes up to 100/spl times/100 pixels in realtime is principally possible. In order to process large images, which are much greater than the physical network, virtual processing is needed, and supported by the hardware. As prototype, a cascadable net of 2/spl times/2 cells is implemented on a chip using the 1.0 /spl mu/ process of ES2.<<ETX>>","PeriodicalId":248898,"journal":{"name":"Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)","volume":"18 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":"114032939","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.1994.381635
Bertram E. Shi
The paper describes a class of nonlinear CNN template which can implement several different types of filters based upon order statistics (L. Pitas and A.N. Venetsanopoulos, 1990). In particular, median, weighted median, rank order filters (such as max and min filters) and M-filters can be implemented, simply by changing the template parameters.<>
{"title":"Order statistic filtering with cellular neural networks","authors":"Bertram E. Shi","doi":"10.1109/CNNA.1994.381635","DOIUrl":"https://doi.org/10.1109/CNNA.1994.381635","url":null,"abstract":"The paper describes a class of nonlinear CNN template which can implement several different types of filters based upon order statistics (L. Pitas and A.N. Venetsanopoulos, 1990). In particular, median, weighted median, rank order filters (such as max and min filters) and M-filters can be implemented, simply by changing the template parameters.<<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":"117101585","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：