Title :
High precision expansion of multi-layer neural networks
Author :
Qianyi Wang;T. Aoyama;U. Nagashima
Author_Institution :
Fac. of Eng., Miyazaki Univ., Japan
fDate :
6/24/1905 12:00:00 AM
Abstract :
We researched high precision multi-layer neural networks for function fittings. We proposed an expansion of neural networks, where the neuron functions (sigmoid-function, sine function series, and variable dumping factors) are used. The expansion improves the fitting precision of the original neural networks in 1000 times.
Keywords :
"Neural networks","Multi-layer neural network","Neurons","Fitting","Computer industry","Sampling methods","Cities and towns","Computer networks","Assembly","Artificial neural networks"
Conference_Titel :
Neural Networks, 2002. IJCNN ´02. Proceedings of the 2002 International Joint Conference on
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007738
