Hierarchical fuzzy neural networks for pattern classification1

Information processing is becoming increasingly important due to the advances of the computing and networking technologies. The systems are required to handle complex, uncertain, and sometimes even contradictory information for a variety of applications. In this chapter, a potential framework of fuzzy neural networks based on hierarchical structures is proposed to provide the ability for robust information processing. Unsupervised and supervised strategies are integrated to train the parameters in the proposed processing framework. Also presented are some promising application examples for biometric authentication, medical image processing, video segmentation, object recognition/detection, and multimedia content-based retrieval.