Extremal Optimization Combined with LM Gradient Search for MLP Network Learning
Gradient search based neural network training algorithm may suffer from local optimum, poor generalization and slow convergence. In this study, a novel Memetic Algorithm based hybrid method with the integration of “extremal optimization” and “Levenberg–Marquardt” is proposed to train multilayer perc...
Main Authors: | Yu-Wang Chen, Peng Chen, Yong-Zai Lu |
---|---|
Format: | Article |
Language: | English |
Published: |
Atlantis Press
2010-11-01
|
Series: | International Journal of Computational Intelligence Systems |
Subjects: | |
Online Access: | https://www.atlantis-press.com/article/2101.pdf |
Similar Items
-
Quantitative Hazard Assessment of Landslides Using the Levenburg–Marquardt Back Propagation Neural Network Method in a Pipeline Area
by: Junnan Xiong, et al.
Published: (2019-10-01) -
Hybridized classification algorithms for data classification applications: A review
by: F. Sherwani, et al.
Published: (2021-07-01) -
Rapid Modeling of the Sound Speed Field in the South China Sea Based on a Comprehensive Optimal LM-BP Artificial Neural Network
by: Jin Huang, et al.
Published: (2021-05-01) -
Comparative analysis of neural network training algorithms for the flood forecast modelling of an alluvial Himalayan river
by: Ruhhee Tabbussum, et al.
Published: (2020-12-01) -
Multi-Scale Parameter Identification of Lithium-Ion Battery Electric Models Using a PSO-LM Algorithm
by: Wen-Jing Shen, et al.
Published: (2017-03-01)