POPFNN-CRI(S) : a fuzzy neural network based on the compositional rule of inference

• المؤلف الرئيسي: Ang, Kai Keng
• مؤلفون آخرون: Quek Hiok Chai
• التنسيق: Theses and Dissertations
• اللغة: English
• منشور في: 2011
• الموضوعات: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• الوصول للمادة أونلاين: http://hdl.handle.net/10356/42627

Fuzzy Neural Networks are hybrid systems that combine the human inference style and natural language description of fuzzy systems with the learning and parallel processing of neural networks. A novel FNN architecture, an improved selforganizing neural network algorithm and two novel fuzzy membership function identification algorithms are proposed. They are the Pseudo Outer-Product based Fuzzy Neural Network using the Compositional Rule of Inference and a Singleton Fuzzifier (POPFNN-CRI(S)), the Modified Learning Vector Quantization (MLVQ) algorithm, the Fuzzy Kohonen Partition (FKP) and the Pseudo Fuzzy Kohonen Partition (PFKP) algorithms.