Modular neural networks optimization with hierarchical genetic algorithms with fuzzy response integration for pattern recognition

作者: Daniela Sánchez , Patricia Melin , Oscar Castillo , Fevrier Valdez

DOI: 10.1007/978-3-642-37798-3_22

关键词:

摘要: In this paper a new model of Modular Neural Network (MNN) with fuzzy integration based on granular computing is proposed. The topology and parameters the MNN are optimized Hierarchical Genetic Algorithm (HGA). proposed method can divide data automatically into sub modules or granules, chooses percentage images selects which will be used for training. responses each module combined using integrator, number integrators depend granules that has at particular moment. was applied to case human recognition illustrate its applicability good results.

参考文章(51)
Soft Computing for Hybrid Intelligent Systems Springer Publishing Company, Incorporated. ,(2008) , 10.1007/978-3-540-70812-4
Denisse Hidalgo, Patricia Melin, Guillerrno Licea, Oscar Castillo, Optimization of Type-2 Fuzzy Integration in Modular Neural Networks Using an Evolutionary Method with Applications in Multimodal Biometry mexican international conference on artificial intelligence. ,vol. 5845, pp. 454- 465 ,(2009) , 10.1007/978-3-642-05258-3_40
Patricia Melin, Oscar Castillo, Soft Computing for Control of Non-Linear Dynamical Systems ,(2001)
Yiyu Yao, A partition model of granular computing Lecture Notes in Computer Science. ,vol. 1, pp. 232- 253 ,(2004) , 10.1007/978-3-540-27794-1_11
Oscar Castillo, Patricia Melin, Type-2 Fuzzy Logic Springer Berlin Heidelberg. pp. 29- 43 ,(2007) , 10.1007/978-3-540-76284-3_3