Pub Date : 2002-07-22DOI: 10.1109/CNNA.2002.1035061
P. Arena, L. Fortuna, M. Frasca, L. Patané
In this paper the topic of including feedback from sensors in the central pattern generator (CPG) for a hexapod robot realized through cellular neural networks (CNNs) is addressed. An approach based on local bifurcation of the CNN cells constituting the sub-units of the CPG network is introduced, allowing control of the direction of the robot. Suitable control can be realized by changing the value of the bias of the CNN cells. Moreover, inspired by the idea of Braitenberg creatures, purely reactive control of the hexapod direction is illustrated with an example of a robot able to avoid obstacles.
{"title":"CNN based central pattern generators with sensory feedback","authors":"P. Arena, L. Fortuna, M. Frasca, L. Patané","doi":"10.1109/CNNA.2002.1035061","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035061","url":null,"abstract":"In this paper the topic of including feedback from sensors in the central pattern generator (CPG) for a hexapod robot realized through cellular neural networks (CNNs) is addressed. An approach based on local bifurcation of the CNN cells constituting the sub-units of the CPG network is introduced, allowing control of the direction of the robot. Suitable control can be realized by changing the value of the bias of the CNN cells. Moreover, inspired by the idea of Braitenberg creatures, purely reactive control of the hexapod direction is illustrated with an example of a robot able to avoid obstacles.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129797525","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.2002.1035101
R. Dogaru, F. Ionescu, P. Julián, M. Glesner
This paper presents state of the art methods for training compact universal CNN cells (or neurons) to represent arbitrary local Boolean functions. The design tools are analyzed and optimized such that they are capable to provide fast solutions for cells with more than 4 inputs. In particular, it is proved statistically that any arbitrary Boolean function with n=5 inputs (corresponding to a von Neumann CNN neighborhood) admits multinested cell realizations thus confirming a conjecture that was previously proven only for n<5. Several hints are also provided regarding the choice and the influence of various parameters of the design algorithms on the quality of the solution and the speed of finding it.
{"title":"Novel methods and results in training universal multi-nested neurons","authors":"R. Dogaru, F. Ionescu, P. Julián, M. Glesner","doi":"10.1109/CNNA.2002.1035101","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035101","url":null,"abstract":"This paper presents state of the art methods for training compact universal CNN cells (or neurons) to represent arbitrary local Boolean functions. The design tools are analyzed and optimized such that they are capable to provide fast solutions for cells with more than 4 inputs. In particular, it is proved statistically that any arbitrary Boolean function with n=5 inputs (corresponding to a von Neumann CNN neighborhood) admits multinested cell realizations thus confirming a conjecture that was previously proven only for n<5. Several hints are also provided regarding the choice and the influence of various parameters of the design algorithms on the quality of the solution and the speed of finding it.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116551435","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.2002.1035046
P. Julián, R. Dogaru, M. Itoh, L. Chua
Concerns a novel structure called the simplicial CNN, which permits one to implement any Boolean/Gray-level function of any number of variables. This paper is devoted to explore novel circuit architectures for the implementation of the simplicial CNN based on resonant tunneling diodes (RTD). The final objective is to implement a fully programmable CNN in a hardware platform based on nanoelectronic devices.
{"title":"On the RTD implementation of simplicial cellular nonlinear networks","authors":"P. Julián, R. Dogaru, M. Itoh, L. Chua","doi":"10.1109/CNNA.2002.1035046","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035046","url":null,"abstract":"Concerns a novel structure called the simplicial CNN, which permits one to implement any Boolean/Gray-level function of any number of variables. This paper is devoted to explore novel circuit architectures for the implementation of the simplicial CNN based on resonant tunneling diodes (RTD). The final objective is to implement a fully programmable CNN in a hardware platform based on nanoelectronic devices.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128118252","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.2002.1035085
P. Foldesy
In this paper a detailed error model is analyzed of the CNN-UM in a general statistical manner. The locally regular template class is considered and the possibility of erroneous output is expressed from the component nonlinearity and parameter deviation.
{"title":"Statistical error modeling of CNN-UM architectures: the binary case","authors":"P. Foldesy","doi":"10.1109/CNNA.2002.1035085","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035085","url":null,"abstract":"In this paper a detailed error model is analyzed of the CNN-UM in a general statistical manner. The locally regular template class is considered and the possibility of erroneous output is expressed from the component nonlinearity and parameter deviation.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114651152","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.2002.1035042
T. Shimizu
The emergence of patterns in a global network, which consists of many connected local networks, is studied. In each local network one of some patterns is stored, which is selected autonomously by the system itself. It is found that global patterns appear in the global system, which are described in terms of 2 patterns stored in local networks as the background and the pattern itself. The relation between dynamics of the local network and the emergence of global patterns in the global network is discussed.
{"title":"Emergence of global patterns in connected neural networks","authors":"T. Shimizu","doi":"10.1109/CNNA.2002.1035042","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035042","url":null,"abstract":"The emergence of patterns in a global network, which consists of many connected local networks, is studied. In each local network one of some patterns is stored, which is selected autonomously by the system itself. It is found that global patterns appear in the global system, which are described in terms of 2 patterns stored in local networks as the background and the pattern itself. The relation between dynamics of the local network and the emergence of global patterns in the global network is discussed.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116707893","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.2002.1035090
R. Bise, N. Takahashi, T. Nishi
This paper presents a design technique which is used to realize associative memories via cellular neural networks. The proposed method can store every prototype vector as a memory vector and maximize the areas of basin of attraction of memory vectors in a certain sense. The network parameters are obtained by solving optimization problems known as generalized eigenvalue problems. Simulation results prove that our method is better than the existing ones.
{"title":"On the design method of cellular neural networks for associative memories based on generalized eigenvalue problem","authors":"R. Bise, N. Takahashi, T. Nishi","doi":"10.1109/CNNA.2002.1035090","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035090","url":null,"abstract":"This paper presents a design technique which is used to realize associative memories via cellular neural networks. The proposed method can store every prototype vector as a memory vector and maximize the areas of basin of attraction of memory vectors in a certain sense. The network parameters are obtained by solving optimization problems known as generalized eigenvalue problems. Simulation results prove that our method is better than the existing ones.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129829724","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.2002.1035100
P. Arena, A. Basile, M. Bucolo, L. Fortuna
In this communication we remark our experience in teaching CNN technologies at the Universita degli Studi di Catania in the course of Adaptive Systems. The main result regards the possibility of using the CNN subject to introduce further topics in circuits and dynamical systems. The students reached high level skills in the related field. Moreover they have developed personalized simulation tools that used to make more experiments confirming that CNN are really the real paradigm for complexity.
{"title":"Teaching CNN and learning by using CNN","authors":"P. Arena, A. Basile, M. Bucolo, L. Fortuna","doi":"10.1109/CNNA.2002.1035100","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035100","url":null,"abstract":"In this communication we remark our experience in teaching CNN technologies at the Universita degli Studi di Catania in the course of Adaptive Systems. The main result regards the possibility of using the CNN subject to introduce further topics in circuits and dynamical systems. The students reached high level skills in the related field. Moreover they have developed personalized simulation tools that used to make more experiments confirming that CNN are really the real paradigm for complexity.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130902622","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.2002.1035050
G. Grassi, L.A. Grieco
Image analysis algorithms are of great interest in the context of object-oriented coding schemes. In this paper a new analogic CNN algorithm for obtaining the motion estimation is illustrated, whereas the companion paper (Grassi and Grieco, 2002) focuses on the remaining steps of the object-oriented image analysis stage. Simulation results, carried out for Miss America and Claire video sequences, confirm the validity of the approach developed herein.
{"title":"Object-oriented image analysis via analogic CNN algorithms. I. Motion estimation","authors":"G. Grassi, L.A. Grieco","doi":"10.1109/CNNA.2002.1035050","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035050","url":null,"abstract":"Image analysis algorithms are of great interest in the context of object-oriented coding schemes. In this paper a new analogic CNN algorithm for obtaining the motion estimation is illustrated, whereas the companion paper (Grassi and Grieco, 2002) focuses on the remaining steps of the object-oriented image analysis stage. Simulation results, carried out for Miss America and Claire video sequences, confirm the validity of the approach developed herein.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122145095","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.2002.1035065
P. López, D. L. Vilariño, D. Cabello
The inherent analogies between the defining equation of CNN and that of heat transfer are well known. In this paper, we explore the projection of a 3D thermal model of the soil on this kind of structure. In so doing, reliable and fast prediction of the thermodynamic behavior of soil subject to known boundary conditions can be obtained. That way, it is possible to characterize different kinds of soil in terms of its thermal signature. Based on that knowledge, and using an inverse approach, we perform the detection of buried land mines.
{"title":"CNN-based 3D thermal modeling of the soil for antipersonnel mine detection","authors":"P. López, D. L. Vilariño, D. Cabello","doi":"10.1109/CNNA.2002.1035065","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035065","url":null,"abstract":"The inherent analogies between the defining equation of CNN and that of heat transfer are well known. In this paper, we explore the projection of a 3D thermal model of the soil on this kind of structure. In so doing, reliable and fast prediction of the thermodynamic behavior of soil subject to known boundary conditions can be obtained. That way, it is possible to characterize different kinds of soil in terms of its thermal signature. Based on that knowledge, and using an inverse approach, we perform the detection of buried land mines.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122391103","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.2002.1035096
I. Szatmári, P. Foldesy, C. Rekeczky, Á. Zarándy
Image Processing Library was designed and is currently under construction for the Aladdin Visual Computer. The library reduces algorithm development time, provides efficient codes, error free operation in binary, and accurate operation in grayscale cases. It is expected that the library will help to spread the use of the CNN technology both in academic fields and in industry.
{"title":"Image processing library for the Aladdin Visual Computer","authors":"I. Szatmári, P. Foldesy, C. Rekeczky, Á. Zarándy","doi":"10.1109/CNNA.2002.1035096","DOIUrl":"https://doi.org/10.1109/CNNA.2002.1035096","url":null,"abstract":"Image Processing Library was designed and is currently under construction for the Aladdin Visual Computer. The library reduces algorithm development time, provides efficient codes, error free operation in binary, and accurate operation in grayscale cases. It is expected that the library will help to spread the use of the CNN technology both in academic fields and in industry.","PeriodicalId":387716,"journal":{"name":"Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2002-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126204963","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：