Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Neural network, self-organization and object extraction
Pattern Recognition Letters - Special issue on artificial neural networks
Image processing and data analysis: the multiscale approach
Image processing and data analysis: the multiscale approach
IEEE Transactions on Image Processing
Efficient and reliable schemes for nonlinear diffusion filtering
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
Benchmark database and GUI environment for printed Arabic text recognition research
WSEAS Transactions on Information Science and Applications
Hi-index | 0.00 |
A self-organizing multilayer neural network suitable for image processing applications is proposed. The output of the neurons in the output layer has been viewed as a fuzzy set and measures of fuzziness have been used to model the error (instability of the network) of the system. Various mathematical models for calculation of fuzziness of this fuzzy set have been described. The weight updating rules under each model have been developed. This error is then back-propagated to correct weights so that the system error is reduced in the next stage. A comparative study (both analytical and experimental) on the rate of learning for different error measures is also done. Results also show that the rate of learning affects the output, especially when the noise level is very high.