Proceedings ArticleDOI
Designing discrete-time cellular neural networks for the evaluation of local Boolean functions
Z. Galias
- pp 23-28
Reads0
Chats0
TLDR
General methods of designing a discrete-time cellular neural network implementing an arbitrary Boolean function defined on the r-neighborhood are described, achieved by operating the network with time-invariant templates as a cellular automaton that processes only binary inputs.Abstract:
General methods of designing a discrete-time cellular neural network implementing an arbitrary Boolean function defined on the r-neighborhood are described. This is achieved by operating the network with time-invariant templates as a cellular automaton that processes only binary inputs. These methods are suitable for solving local tasks. As an example, testing minimal distances is discussed. >read more
Citations
More filters
Journal ArticleDOI
Multiple layer discrete-time cellular neural networks using time-variant templates
TL;DR: A generalized architecture for discrete-time cellular neural networks (DTCNNs) is provided, which allows multiple layers of different architecture, which can be combined in several interconnection modes.
Journal ArticleDOI
Pyramidal cells: a novel class of adaptive coupling cells and their applications for cellular neural networks
TL;DR: The defining formula, the main properties, and several applications of a novel coupling cell are presented, which suggest a VLSI implementation of CNNs based on pyramidal cells offers a speedup of up to one million times when compared to corresponding software implementations.
Journal ArticleDOI
Designing cellular neural networks for the evaluation of local Boolean functions
TL;DR: Describes general methods for designing a cellular neural network implementing an arbitrary Boolean function defined on the r-neighborhood by operating the network with time-variant templates as a cellular automaton that processes only binary inputs.
Proceedings ArticleDOI
Optimizing the morphological design of discrete-time cellular neural networks
TL;DR: A hardware reduction scheme of morphologically designed DTCNNs is proposed which includes the introduction of time variant templates and the identification of non-elementary expressions for which a single layer D TCNN exists.
References
More filters
Journal ArticleDOI
Discrete-time cellular neural networks
Hubert Harrer,Josef A. Nossek +1 more
TL;DR: 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.
Book
Modern Cellular Automata: Theory and Applications
TL;DR: A comparison study of two-Dimensional Logical Transforms in N-Space and their applications in scientific and biomedical research.
Journal ArticleDOI
Cellular neural networks: Theory and circuit design
TL;DR: An abstract normalized definition of cellular neural networks with arbitrary interconnection topology is given and the property of convergence is found to be of central importance: large classes of convergent CNNs in practice always asymptotically approach some stable equilibrium where each component of the corresponding output is binary-valued.
Related Papers (5)
Memristor cellular automata and memristor discrete-time cellular neural networks
Makoto Itoh,Leon O. Chua +1 more