Fast-convergence learning algorithms for multi-level and binary neurons and solution of some image processing problems
In this paper we consider fast-convergence learning algorithms for multi-valued and universal binary neurons. These neurons are suggested to be used for the design of neural networks based on Cellular Neural Networks (CNN) —in the sense of connections between neurons. On the basis of such networks we offer a solution to some problems of image processing. For instance, a highly efficient method for contours distinguishing, obtained by the learning algorithm described in this paper is presented.
Unable to display preview. Download preview PDF.
- L.O. Chua and L. Yang, “Cellular neural networks: Theory”, IEEE Trans. Circuits Syst., vol. 5, pp. 1257–1290, Oct. 1988.Google Scholar
- Proceedings of the 1990 IEEE International Workshop on CNN and their applications (CNNA-90). Budapest, 1990, IEEE Catalog No. 90TH0312-9.Google Scholar
- Proceedings of the Second International Workshop on Cellular Neural Networks and their Applications (CNNA-92), Munich 1992. IEEE Catalog No. 92TH0498-6.Google Scholar
- N. N. Aizenberg and I. N. Aizenberg, “Model of the Neural Networks basic elements (cells) with universal functionality and various hardware implementations”, Proc. of the 2nd International Conf. on Microelectronics for Neural Networks, Munich, Kirill & Methody Verlag, 1991, pp. 77–82.Google Scholar
- N. N. Aizenberg and I. N. Aizenberg, “CNN based on multi-valued neuron as a model of associative memory for grey-scale images”, Proc. of the 2nd International Workshop CNNA-92, Munich, 1992, IEEE Catalog No. 92TH0498-6, pp. 36–41.Google Scholar
- W. K. Pratt “Digital Image Processing” John Wiley & Sons Publisher House, N.Y. 1978.Google Scholar