{"title":"On the Periodic Solutions in One Dimensional Cellular Nonlinear Networks Based on Josephson Junctions (JJ's)","authors":"V. Mladenov, A. Slavova","doi":"10.1109/CNNA.2006.341637","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341637","url":null,"abstract":"In this paper we consider an autonomous one dimensional cellular nonlinear network (CNN) that consists of chain of N simple cells based on Josephson Junctions (JJ's) coupled by linear inductors. In fact the subject is the well known Josephson Transmission Line (JTL) that is used in many applications in superconductor electronics and more especially in Rapid Single Flux Quantum (RSFQ) technique. When the last cell is connected with the first one a ring of Josephson Junctions is formed. Using the framework of the cellular nonlinear network we consider the JTL under the umbrella of the system theory. Based on describing functions method we rigorously prove the existence and stability of periodic solutions in the cellular nonlinear network model considered. The results are confirmed by simulations","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124878115","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}
L. Spaanenburg, B. Akesson, A. Hansson, K. Goossens
{"title":"Design Method for Unconventional Computing","authors":"L. Spaanenburg, B. Akesson, A. Hansson, K. Goossens","doi":"10.1109/CNNA.2006.341655","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341655","url":null,"abstract":"Network-on-chip concepts allow moving away from the classical, centralized computer. The meaningful collaboration of computing units over a well-behaved network creates the infinite state space that underlies the Turing computer concept. The combinatorial state explosion that results from a network-on-chip will easily prove more valuable than the mere technological progress in memory storage, when the network nodes become small enough. Embedded super-computing has this unconventional goal. This paper introduces a design method for such computing concepts. It discusses how a software simulation is gradually migrated into a network-on-chip implementation. The approach is illustrated by the development of a cellular neural network as a typical example of a well-behaved network on small, embedded nodes","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116450501","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}
{"title":"A Pattern Classification Method Based on a Space-Variant CNN Template","authors":"G. Costantini, D. Casali, M. Carota","doi":"10.1109/CNNA.2006.341633","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341633","url":null,"abstract":"A novel algorithm for unsupervised classification of datasets made up of integer valued patterns by means of cellular neural network (CNN) is proposed. The algorithm is suited both for linearly separable and nonlinearly separable data sets. The adopted CNN is n-dimensional and is based on a space-variant template - neighborhood order 1 - to cluster n-dimensional datasets. The choice of a CNN architecture allows a straightforward hardware implementation, particularly suited for bi-dimensional patterns","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"345 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115983534","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}
{"title":"N-Scroll Generation in SC-CNN via NeuroFuzzy Based Nonlinear Function","authors":"T. Gunay, M. Alçı, S. Parmaksizoglu","doi":"10.1109/CNNA.2006.341634","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341634","url":null,"abstract":"A new way of generating n-scroll chaotic attractors is presented. A neurofuzzy controller is used to obtain the piecewise-linear function of the state controlled cellular neural network system. It can be seen from the computer simulations that the proposed model can be able to produce double-scroll to 5-scroll attractors","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132324863","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}
{"title":"On the Feature Extraction Performances of CNN Gabor-Type Filters in Texture Recognition Applications","authors":"E. David, P. Ungureanu, L. Goras","doi":"10.1109/CNNA.2006.341621","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341621","url":null,"abstract":"This paper presents several results regarding the feature extraction performances of 2D CNN Gabor type filter banks in a texture recognition application. These performances are studied for circular symmetric or separable frequency response filters with several filter neighborhood radii and parameters. The results are compared with similar approaches from literature","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134219160","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}
{"title":"Towards Analog VLSI Arrays for Nonseparable 3D Spatiotemporal Filtering","authors":"Emmanuel M. Drakakis","doi":"10.1109/CNNA.2006.341624","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341624","url":null,"abstract":"We report the development of a new CNN based theoretical framework and its on-going analog VLSI implementation for continuous-time discrete-space spatiotemporal filtering. Our proposed formulation, which stems from the theory of linear cellular neural networks, is capable of realizing a wide range of linear spatiotemporal dynamics. Based on our proposed framework, 3D nonseparable spatiotemporal filters are synthesized. The filters are presented in the form of continuous-time/discrete-space mixed domain transfer functions with responses qualitatively resembling visual cortical bandpass spatiotemporal receptive fields. Analog VLSI building blocks suitable for the implementation of the required spatiotemporal dynamics are presented. Simulation results on AMS 0.35mum process parameters of a 5times5 array, with electrical parameters tuned to realize the spatiotemporal dynamics of one of our synthesized 3D bandpass filters, are presented","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128295160","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}
{"title":"FPGA Based Implementation of Water Reinjection in Geothermal Structure","authors":"S. Kocsárdi, Z. Nagy, S. Kostianev, P. Szolgay","doi":"10.1109/CNNA.2006.341653","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341653","url":null,"abstract":"In the area of geophysical and mining engineering the solution of partial differential equations (PDE) has been one of the most important problems of mathematics for a long time. Inside that one of the most exciting fields is the simulation of geothermal processes which can be used in the everyday energy-management. In this contribution a CNN-UM simulation of water reinjection are presented. Unfortunately the three dimensional - or the coupled multi-layered - computational structure and space-variant templates do not make it possible to utilize the huge computing power of the analog CNN-UM chips. To improve the performance of our solution an emulated digital CNN-UM has been used","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129808846","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}
{"title":"Prediction Error Profiles allowing a Seizure Forecasting in Epilepsy ?","authors":"Christian Niederhoefer, R. Tetzlaff","doi":"10.1109/CNNA.2006.341607","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341607","url":null,"abstract":"Although a large number of publications has appeared, the problem of seizure forecasting in epilepsy remains unsolved up to now. The main problem is the derivation of EEG signal features, which show distinct changes of an impending epileptic seizure, occurring as seizure precursors. In previous publications (Niederhofer and Tetzlaff, 2005) several approaches to the feature extraction problem based on Volterra-Systems (VS) and cellular nonlinear networks (CNN) (Chua, 1998) have been proposed. Because distinct changes in the behaviour of discrete-time CNN predictor systems have been observed before the onsets of seizures, a deeper analysis of long lasting recordings of EEG signals will be given throughout this contribution","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132871899","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}
Ediuardo Gomez-Ramirez, G. E. Pazienza, X. Vilasis-Cardona
{"title":"Polynomial Discrete Time Cellular Neural Networks to solve the XOR problem","authors":"Ediuardo Gomez-Ramirez, G. E. Pazienza, X. Vilasis-Cardona","doi":"10.1109/CNNA.2006.341598","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341598","url":null,"abstract":"Some papers discuss different options to improve the capabilities of cellular neural networks (CNN). The principal point is that a single layer CNN can not solve problems with linearly nonseparable data. In this paper a new model called polynomial discrete time cellular neural networks is presented. This model has a very simple nonlinear term that can improve the performance of the network. The results show how it is possible to solve the XOR problem. The templates of the entire network are computed using genetic algorithm","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123084836","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}
{"title":"Modeling of elastic inter-node bounds in Cellular Neural Network-based implementation of the deformable grid paradigm","authors":"P. Korbel, K. Slot","doi":"10.1109/CNNA.2006.341612","DOIUrl":"https://doi.org/10.1109/CNNA.2006.341612","url":null,"abstract":"The following paper extends a method of deformable grid paradigm implementation by providing modeling of elastic node interactions. The proposed method is based on parallel estimation of between-node distances, which is done by execution of appropriately arranged constrained diffusion procedure. Since, due to the introduced node interaction mechanism, nodes can get arbitrarily displaced, an appropriate method of modeling of the other component of the deformable grid paradigm - grid-image image interaction s also provided","PeriodicalId":430348,"journal":{"name":"2006 10th International Workshop on Cellular Neural Networks and Their Applications","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121056179","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}