DocumentCode :
2287825
Title :
On the Levenberg-Marquardt training method for feed-forward neural networks
Author :
Liu, Hongwei
Author_Institution :
Sch. of Inf., Beijing Wuzi Univ., Beijing, China
Volume :
1
fYear :
2010
fDate :
10-12 Aug. 2010
Firstpage :
456
Lastpage :
460
Abstract :
The Levenberg-Marquardt (LM) training method is the most effective method for feed-forward neural networks with respect to the training precision. This method is well-known and popularly described in the neural networks literature. Nevertheless its implementation contains some difficulties because of the specific shape of the cost function and the large amount of variables. Here we give in sufficient details an example of a program implementation of the LM training method. This implementation (as a Matlab application) seems to work well with various examples.
Keywords :
feedforward neural nets; optimisation; Levenberg Marquardt training method; Matlab application; cost function; feedforward neural networks; neural networks literature; Artificial neural networks; Biological neural networks; Cost function; Jacobian matrices; Neurons; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation (ICNC), 2010 Sixth International Conference on
Conference_Location :
Yantai, Shandong
Print_ISBN :
978-1-4244-5958-2
Type :
conf
DOI :
10.1109/ICNC.2010.5583151
Filename :
5583151
Link To Document :
بازگشت