Title :
Structural learning with M-apoptosis in neurofuzzy GMDH
Author :
Ohtani, Takashi ; Ichihashi, Hidetomo ; Miyoshi, Tetsuya ; Nagasaka, Kazunori
Author_Institution :
Osaka Prefecture Univ., Japan
Abstract :
There have been many studies of mathematical models of neural networks. However, there is always a problem of determining their optimal structures because of the lack of prior information. Apoptosis is the mechanism responsible for the physiological deletion of cells and appears to be intrinsically programmed. We propose a procedure, named M-apoptosis, for the structure clarification of neurofuzzy GMDH model whose partial descriptions are represented by the radial basis functions network. The proposed method prunes unnecessary links and units from the larger network to identify, and to further clarify the network structure by minimizing the Minkowski norm of the derivatives of the partial descriptions. The method is validated in the numerical examples of function approximation and the classification of Fisher´s Iris data
Keywords :
feedforward neural nets; function approximation; fuzzy neural nets; identification; learning (artificial intelligence); pattern classification; Fisher Iris data; Minkowski norm; apoptosis; function approximation; group method of data handling; mathematical models; neurofuzzy GMDH; pattern classification; pruning algorithm; radial basis functions network; structural learning; Biological neural networks; Central nervous system; Data handling; Function approximation; Input variables; Intelligent networks; Iris; Organizing; Physiology; Radial basis function networks;
Conference_Titel :
Fuzzy Systems Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4863-X
DOI :
10.1109/FUZZY.1998.686300