Interval Type-2 Fuzzy Logic for Improving Feature Extraction and Response Integration in Modular Neural Networks for Image Recognition
Olivia D. Mendoza, Patricia Melín, Oscar Castillo · ASME Press eBooks · 2007
The combination of Soft Computing techniques allows the improvement of intelligent systems with different hybrid approaches. In this work we consider two parts of a Modular Neural Network for image recognition, where a Type-2 Fuzzy Inference System (FIS 2) makes a great difference. The first FIS 2 is used for feature extraction in training data, and the second one to find the ideal parameters for the integration method of the modular neural network.