Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035055
W. Singer
Psychophysical and neurophysiological evidence indicates that the brain identifies perceptual objects by decomposing them into components by analyzing the relations among the respective components and representing in a combined code the components and their specific relations. This is an efficient strategy for two reasons. First, it permits unambiguous descriptions of a virtually unlimited number of perceptual objects with a limited set of symbols for components and relations. Second, it can be scaled and applied also for the description of complex constellations, i.e. for the infinite variety of contextual configurations in which perceptual objects can occur. Linguistic descriptions follow the same principle. By recombining in ever changing configurations a rather limited set of symbols for components, properties and relations, a virtually inexhaustible universe of constellations can be encoded. However, there is an interesting trade-off between the complexity of the symbols and the syntactic rules required for the definition of relations.
{"title":"Time as coding space for information processing in the cerebral cortex","authors":"W. Singer","doi":"10.1109/CNNA.2002.1035055","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035055","url":null,"abstract":"Psychophysical and neurophysiological evidence indicates that the brain identifies perceptual objects by decomposing them into components by analyzing the relations among the respective components and representing in a combined code the components and their specific relations. This is an efficient strategy for two reasons. First, it permits unambiguous descriptions of a virtually unlimited number of perceptual objects with a limited set of symbols for components and relations. Second, it can be scaled and applied also for the description of complex constellations, i.e. for the infinite variety of contextual configurations in which perceptual objects can occur. Linguistic descriptions follow the same principle. By recombining in ever changing configurations a rather limited set of symbols for components, properties and relations, a virtually inexhaustible universe of constellations can be encoded. However, there is an interesting trade-off between the complexity of the symbols and the syntactic rules required for the definition of relations.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129293539","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035097
Z. Zhang, E.M. Namba, S. Takatori, H. Kawabata
Setting the optimal values of the neighborhood is an important factor for improving a CNN's capability. In this paper, we propose a new design method for the neighborhood, which reduces the computation time while maintaining its capability. In order to examine its effectiveness, we use synthesized model patterns and confirm whether the efficiency is improved. In addition, we apply the CNN designed to diagnosing abnormal sounds and obtained very encouraging results.
{"title":"A new design method for the neighborhood on improving the CNN's efficiency","authors":"Z. Zhang, E.M. Namba, S. Takatori, H. Kawabata","doi":"10.1109/CNNA.2002.1035097","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035097","url":null,"abstract":"Setting the optimal values of the neighborhood is an important factor for improving a CNN's capability. In this paper, we propose a new design method for the neighborhood, which reduces the computation time while maintaining its capability. In order to examine its effectiveness, we use synthesized model patterns and confirm whether the efficiency is improved. In addition, we apply the CNN designed to diagnosing abnormal sounds and obtained very encouraging results.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126057599","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035041
A. Selikhov
A mL-CNN is presented in this paper as a generalization of CNN models of reaction-diffusion processes in nonlinear media with m components. Main properties of the model are considered in accordance with imaginations of the process "mechanisms". Two particular CNN models, an autonomous 2L-CNN and a 2L-CNN with external inputs, are presented as examples of special cases of the mL-CNN. Emergence of some complex phenomena in such particular models are also shown.
{"title":"mL-CNN: a CNN model for reaction-diffusion processes in m-component systems","authors":"A. Selikhov","doi":"10.1109/CNNA.2002.1035041","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035041","url":null,"abstract":"A mL-CNN is presented in this paper as a generalization of CNN models of reaction-diffusion processes in nonlinear media with m components. Main properties of the model are considered in accordance with imaginations of the process \"mechanisms\". Two particular CNN models, an autonomous 2L-CNN and a 2L-CNN with external inputs, are presented as examples of special cases of the mL-CNN. Emergence of some complex phenomena in such particular models are also shown.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126103336","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035030
M. Gilli, T. Roska, L. Chua, P. Civalleri
The relationship between cellular neural/nonlinear networks (CNNs) and partial differential equations (PDEs) is investigated. The equivalence between a discrete-space CNN model and a continuous-space PDE model is rigorously defined. The problem of the equivalence is split into two sub-problems: approximation and topological equivalence, that can be explicitly studied for any CNN models. It is known that each PDE can be approximated by a space difference scheme, i.e. a CNN model, that presents a similar dynamic behavior. It is shown, through examples, that there exist CNN models that are not equivalent to any PDEs, either because they do not approximate any PDE models, or because they have a different dynamic behavior (i.e. they are not topologically equivalent to the PDE, that approximate). This proves that the spatio-temporal CNN dynamics is broader than that described by PDEs.
{"title":"On the relationship between CNNs and PDEs","authors":"M. Gilli, T. Roska, L. Chua, P. Civalleri","doi":"10.1109/CNNA.2002.1035030","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035030","url":null,"abstract":"The relationship between cellular neural/nonlinear networks (CNNs) and partial differential equations (PDEs) is investigated. The equivalence between a discrete-space CNN model and a continuous-space PDE model is rigorously defined. The problem of the equivalence is split into two sub-problems: approximation and topological equivalence, that can be explicitly studied for any CNN models. It is known that each PDE can be approximated by a space difference scheme, i.e. a CNN model, that presents a similar dynamic behavior. It is shown, through examples, that there exist CNN models that are not equivalent to any PDEs, either because they do not approximate any PDE models, or because they have a different dynamic behavior (i.e. they are not topologically equivalent to the PDE, that approximate). This proves that the spatio-temporal CNN dynamics is broader than that described by PDEs.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130115026","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035079
M. Laiho, A. Paasio, A. Kananen, K. Halonen
In this paper realization of couplings between cells in a polynomial type mixed-mode cellular neural network (CNN) is analyzed. One quadrant operation is required from the analog multipliers and polynomial circuits because in a mixed-mode CNN extension to four quadrant operation can be done digitally. A one quadrant multiplier is analyzed and simulated with HSPICE. Furthermore, circuits for generating second and third order polynomial terms of cell output are analyzed and HSPICE simulations are shown.
{"title":"Realization of couplings in a polynomial type mixed-mode CNN","authors":"M. Laiho, A. Paasio, A. Kananen, K. Halonen","doi":"10.1109/CNNA.2002.1035079","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035079","url":null,"abstract":"In this paper realization of couplings between cells in a polynomial type mixed-mode cellular neural network (CNN) is analyzed. One quadrant operation is required from the analog multipliers and polynomial circuits because in a mixed-mode CNN extension to four quadrant operation can be done digitally. A one quadrant multiplier is analyzed and simulated with HSPICE. Furthermore, circuits for generating second and third order polynomial terms of cell output are analyzed and HSPICE simulations are shown.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114763673","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035105
M. Jakubowski, S. Jankowski
This paper presents the design of a digital integrated circuit implementation of fully programmable cellular neural network for binary images processing. It consists of 16/spl times/16 cells and the memory able to store the image. The circuit is design in the standard cell style CMOS 0.35 /spl mu/m technology. The advantages of the digital CNN are: high reliability and robustness to the manufacturing parameters disturbances in comparison with analogue implementation. The disadvantages of this approach are: higher power consumption and larger IC silicon area. The paper presents the architecture of the network, as well as its components, the estimated system parameters (calculation speed, power consumption and density of cells) in comparison to selected CNN designs.
{"title":"Design of IC implementation of 16/spl times/16 CNN with serial-parallel input","authors":"M. Jakubowski, S. Jankowski","doi":"10.1109/CNNA.2002.1035105","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035105","url":null,"abstract":"This paper presents the design of a digital integrated circuit implementation of fully programmable cellular neural network for binary images processing. It consists of 16/spl times/16 cells and the memory able to store the image. The circuit is design in the standard cell style CMOS 0.35 /spl mu/m technology. The advantages of the digital CNN are: high reliability and robustness to the manufacturing parameters disturbances in comparison with analogue implementation. The disadvantages of this approach are: higher power consumption and larger IC silicon area. The paper presents the architecture of the network, as well as its components, the estimated system parameters (calculation speed, power consumption and density of cells) in comparison to selected CNN designs.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122466229","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035071
M. Salerno, F. Sargeni, V. Bonaiuto
In this paper a hardware implementation of a PDE analogue simulator is presented. In particular, this circuit is able to manage reaction-diffusion partial differential equations by using a cellular nonlinear network (CNN).
{"title":"PDE-DPCNN: a CNN chip for analogue simulations of RD equations","authors":"M. Salerno, F. Sargeni, V. Bonaiuto","doi":"10.1109/CNNA.2002.1035071","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035071","url":null,"abstract":"In this paper a hardware implementation of a PDE analogue simulator is presented. In particular, this circuit is able to manage reaction-diffusion partial differential equations by using a cellular nonlinear network (CNN).","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124878504","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035039
D. L. Vilariño, D. Cabello, V. Brea
This paper addresses the application of the pixel level snakes for the segmentation of moving objects. This kind of active contour techniques can handle multiple contours simultaneously without time-processing penalty as well as to manage appropriately the topologic transformations among them when this is required. The implementation into a CNNUM or a specific purpose CNN platform gives solution to the speed requirements of this kind of tasks. Particularly, we show an analogic CNN-algorithm which meets all the constrains imposed for the current CNNUM hardware implementations.
{"title":"An analogic CNN-algorithm of pixel level snakes for tracking and surveillance tasks","authors":"D. L. Vilariño, D. Cabello, V. Brea","doi":"10.1109/CNNA.2002.1035039","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035039","url":null,"abstract":"This paper addresses the application of the pixel level snakes for the segmentation of moving objects. This kind of active contour techniques can handle multiple contours simultaneously without time-processing penalty as well as to manage appropriately the topologic transformations among them when this is required. The implementation into a CNNUM or a specific purpose CNN platform gives solution to the speed requirements of this kind of tasks. Particularly, we show an analogic CNN-algorithm which meets all the constrains imposed for the current CNNUM hardware implementations.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121990831","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035051
G. Grassi, L.A. Grieco
For pt.I see ibid., p.172-9 (2002). In the context of image analysis for object-oriented coding schemes, this paper presents new analogic CNN algorithms for implementing the image synthesis and consistency observation stages. Along with the motion estimation algorithm illustrated in the companion paper, the proposed approach represents a framework for implementing CNN-based real-time image analysis. Simulation results, carried out for Miss America video sequence, confirm the validity of the algorithms developed herein.
{"title":"Object-oriented image analysis via analogic CNN algorithms. II. Image synthesis and consistency observation","authors":"G. Grassi, L.A. Grieco","doi":"10.1109/CNNA.2002.1035051","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035051","url":null,"abstract":"For pt.I see ibid., p.172-9 (2002). In the context of image analysis for object-oriented coding schemes, this paper presents new analogic CNN algorithms for implementing the image synthesis and consistency observation stages. Along with the motion estimation algorithm illustrated in the companion paper, the proposed approach represents a framework for implementing CNN-based real-time image analysis. Simulation results, carried out for Miss America video sequence, confirm the validity of the algorithms developed herein.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128490751","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 : 2002-07-22DOI: 10.1109/CNNA.2002.1035037
L. Koskinen, M. Laiho, A. Paasio, K. Halonen
The suitability of an existing cellular nonlinear network (CNN) chip for MPEG-4 core profile shape segmentation is investigated. The chip and the algorithm it is based on are found to be suitable for shape segmentation and additional templates are proposed to enhance the chip's MPEG-4 suitability. Additional uses for the CNN chip are found in MPEG-4 encoder computational power demand reduction.
{"title":"MPEG-4 based modifications for an CNN segmentation chip","authors":"L. Koskinen, M. Laiho, A. Paasio, K. Halonen","doi":"10.1109/CNNA.2002.1035037","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035037","url":null,"abstract":"The suitability of an existing cellular nonlinear network (CNN) chip for MPEG-4 core profile shape segmentation is investigated. The chip and the algorithm it is based on are found to be suitable for shape segmentation and additional templates are proposed to enhance the chip's MPEG-4 suitability. Additional uses for the CNN chip are found in MPEG-4 encoder computational power demand reduction.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127396716","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：