Title :
An improved Levenberg-Marquardt learning algorithm for neural networks based on terminal attractors
Author :
Batbayar, Batsukh ; Yu, Xinghuo
Author_Institution :
Sch. of Electr. & Comput. Eng., RMIT Univ., Melbourne, VIC
Abstract :
In this paper, an improved Levenberg-Marquardt learning algorithm based on terminal attractors for feedforward neural networks is proposed. The effectiveness of the proposed algorithm in improving learning speed is shown by the simulation results.
Keywords :
feedforward neural nets; learning (artificial intelligence); Levenberg-Marquardt learning algorithm; feedforward neural networks; terminal attractors; Australia; Backpropagation algorithms; Biomedical optical imaging; Computational modeling; Computer networks; Convergence; Feedforward neural networks; Neural networks; Optical character recognition software; Optical computing;
Conference_Titel :
Systems and Control in Aerospace and Astronautics, 2008. ISSCAA 2008. 2nd International Symposium on
Conference_Location :
Shenzhen
Print_ISBN :
978-1-4244-3908-9
Electronic_ISBN :
978-1-4244-2386-6
DOI :
10.1109/ISSCAA.2008.4776198
