Nonlinear fitting by using a neural net algorithm

To improve the performance of the neural network training procedure, a transfer function for normalized data set and a modified conjugate gradient algorithm were proposed. Results were better than that of principal component regression and partial least square regression.

Saved in:
Bibliographic Details
Published inAnalytical chemistry (Washington) Vol. 65; no. 4; pp. 393 - 396
Main Authors Li, Zheng, Cheng, Zhaonian, Xu, Li, Li, Tonghua
Format Journal Article
LanguageEnglish
Published Washington, DC American Chemical Society 15.02.1993
Subjects
Algorithms
Applied sciences
Chemistry
Devices using thermal energy
Energy
Energy. Thermal use of fuels
Exact sciences and technology
Furnaces
Mathematical models
Metals. Metallurgy
Non linear fitting
Refractory
Lifetime
Theoretical study
Lining
Neural network
Transfer function
Algorithm
Metallurgical furnace
Online AccessGet full text
ISSN0003-2700
1520-6882
DOI10.1021/ac00052a014

Cover

More Information
Summary:To improve the performance of the neural network training procedure, a transfer function for normalized data set and a modified conjugate gradient algorithm were proposed. Results were better than that of principal component regression and partial least square regression.
Bibliography:ark:/67375/TPS-L987S6XR-M
istex:768FA3310F5A18675396EEE5DEE711627A1BEB98
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ISSN:0003-2700
1520-6882
DOI:10.1021/ac00052a014