share
Acta Chimica Sinica ›› 1996, Vol. 54 ›› Issue (10): 1009-1015. Previous Articles Next Articles
Original Articles
李志良;曾鸽鸣;梁本熹;邱细敏;胡芳;李梦龙
发布日期:
LI ZHILIANG;ZENG GEMING;LIANG BENXI;QIU XIMIN;HU FANG;LI MENGLONG
Published:
Share
Backpropagation (BP), one of the most useful algorithms to train neural networks (NN), has some deficiencies and/or inadequacies such as low convergence and local optima. A novel learning method for training NN, extended Kalman filtering (EF), has been developed with rapid convergence speed, few iteration cycles and small hidden neurons. This EFNN method was used for multicomponent spectral resolution and simultaneous determination of composite pharmaceutical APC preparations and mixed aromatic species samples with satisfactory results.
Key words: NEURAL NETWORK
CLC Number:
O657
LI ZHILIANG;ZENG GEMING;LIANG BENXI;QIU XIMIN;HU FANG;LI MENGLONG. Extended Kalman filtering tranined neural networks and its applications to multicomponent spectral resolution[J]. Acta Chimica Sinica, 1996, 54(10): 1009-1015.
Export EndNote|Reference Manager|ProCite|BibTeX|RefWorks