On the separating capability of cellular neural networks
β Scribed by Osuna, J. A.; Moschytz, G. S.
- Publisher
- John Wiley and Sons
- Year
- 1996
- Tongue
- English
- Weight
- 456 KB
- Volume
- 24
- Category
- Article
- ISSN
- 0098-9886
No coin nor oath required. For personal study only.
β¦ Synopsis
The cellular neural network is able to perform different image-processing tasks depending on the template values, i.e. the network parameters, used. In the case of linear templates the parameter space is divided into different regions by hyperplanes. Every region is associated with a task, such that all points within that region let the cellular neural network perform the desired task. In this paper a lower and an upper bound for the number of regions that can be separated with binary-input cellular neural networks are given, thus answering the question of how many differenttasks such a cellular neural network can perform.
π SIMILAR VOLUMES
The sensitivity of cellular neural networks (CNN) against random parameter deviations is discussed in detail. For di erent CNN with erroneous parameters the probability is estimated that all cell outputs converge to the same stable ΓΏxpoint of the corresponding error free CNN. These results are compa
This paper is concerned with the invertibility of parallel operations definable on two-dimensional binary arrays by means of a local Boolean function. In this way, it contributes to the theory of cellular automata and may open new potentialities to cellular neural network applications. We provide a
This special issue on CNN addresses three areas: theory, design, and applications. It is clear from the table of contents that most of the advances reported here are, explicitly or tacitly, influenced by the existence of the programmable CNN universal machine chips. A new programming discipline, the
Classification among groups is a crucial problem in managerial decision making. Classification techniques are used in: identifying stressed firms, classifying among consumer types, and rating of firms' bonds, etc. Neural networks are recognized as important and emerging methodologies in the area of