Neural network architectures: an introduction
Neural network architectures: an introduction
Enhanced fuzzy single layer perceptron
ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Hi-index | 0.00 |
In this paper, we proposed an enhanced fuzzy single layer learning algorithm using the dynamic adjustment of threshold. For performance evaluation, the proposed method was applied to the XOR problem, which is used as a benchmark in the field of pattern recognition, and the recognition of digital image in a practical image processing application. As a result of experiment, though the method does not always guarantee the convergence, it shows the improved learning time and the high convergence rate.