Journal ArticleDOI
Discrete-time cellular neural networks
Hubert Harrer,Josef A. Nossek +1 more
TLDR
Convergence is proved for a large class of templates and applications are given for the following image-processing tasks: linear thresholding, connected component detection, hole filling, concentric contouring, increasing and decreasing objects step by step, searching for objects with minimal distance, and oscillation.Abstract:
A network structure called a discrete-time cellular neural network is introduced. It is derived from cellular neural networks and feedback threshold networks. the architecture is discussed and its advantages are presented. Convergence is proved for a large class of templates and applications are given for the following image-processing tasks: linear thresholding, connected component detection, hole filling, concentric contouring, increasing and decreasing objects step by step, searching for objects with minimal distance, and oscillation.read more
Citations
More filters
Journal ArticleDOI
The CNN paradigm
Leon O. Chua,Tamás Roska +1 more
TL;DR: In this article, the cellular neural network (CNN) paradigm is given, along with a precise taxonomy and a concise tutorial description of the CNN paradigm, and the canonical equations are described.
Journal ArticleDOI
A comprehensive review for industrial applicability of artificial neural networks
TL;DR: An organized and normalized review of the industrial applications of artificial neural networks, in the last 12 years, is presented to help industrial managing and operational personnel decide which kind of ANN topology and training method would be adequate for their specific problems.
Journal ArticleDOI
The global stability of fuzzy cellular neural network
Tao Yang,Lin-Bao Yang +1 more
TL;DR: In this article, the global stability of fuzzy cellular neural networks (FCNNs) is investigated and conditions under which a FCNN has only one globally stable equilibrium point are given.
Journal ArticleDOI
Training cellular automata for image processing
TL;DR: The sequential floating forward search method for feature selection was used to select good rule sets for a range of tasks, namely noise filtering, noise filtering using threshold decomposition, thinning, and convex hulls.
Journal ArticleDOI
Impulsive Stabilization and Impulsive Synchronization of Discrete-Time Delayed Neural Networks
TL;DR: By introducing the time-varying Lyapunov functional to capture the dynamical characteristics of discrete-time impulsive delayed neural networks (DIDNNs) and by using a convex combination technique, new exponential stability criteria are derived in terms of linear matrix inequalities.
References
More filters
Journal ArticleDOI
Cellular neural networks: theory
Leon O. Chua,L. Yang +1 more
TL;DR: In this article, a class of information processing systems called cellular neural networks (CNNs) are proposed, which consist of a massive aggregate of regularly spaced circuit clones, called cells, which communicate with each other directly through their nearest neighbors.
Journal ArticleDOI
Cellular neural networks: applications
Leon O. Chua,Lin-Bao Yang +1 more
TL;DR: Examples of cellular neural networks which can be designed to recognize the key features of Chinese characters are presented and their applications to such areas as image processing and pattern recognition are demonstrated.
Journal Article
Cellular automata machines
TL;DR: A cellular automata machine is a computer optimized for the simulation of cellular Automata that allows it to run thousands of times faster than a general-purpose computer of comparable cost programmed to do the same task.
Journal ArticleDOI
Decreasing energy functions as a tool for studying threshold networks
TL;DR: Block sequential iterations of threshold networks are studied through the use of a monotonic operator, analogous to the spin glass energy, which allows to characterize the dynamics: transient and fixed points.
Journal ArticleDOI
Stability of a class of nonreciprocal cellular neural networks
Leon O. Chua,Tamás Roska +1 more
TL;DR: In this article, it is shown that symmetry (reciprocity) is in general not necessary for complete stability of cellular neural networks and the conditions discussed are robust in the sense that they require neither precise template-value relations nor a closeness to some prescribed values.