Research on the Optimized Algorithms on Neural Network

Xiao Qin Wu

doi:10.4028/www.scientific.net/AMR.605-607.2175

Paper Titles

Morphological Reconstruction Based Segmentation of Lung Fields on Digital Radiographs
p.2155

Coordination Method on Cloud Computing Clusters
p.2160

The Method of Feature Extraction of Weak Multi-Frequency Signals Based on the Array of Modulated Stochastic Resonance
p.2164

The Fusion Process of RS(Remote Sensing) Data Based on Wavelet Neural Network
p.2171

Research on the Optimized Algorithms on Neural Network
p.2175

Classification of Single Cereal Grain Kernel Using Shape Parameters Based on Machine Vision
p.2179

Detection for Corn/Weed Images Using Moment Invariants by BPNN Classifier
p.2183

On Implementation of Software Acoustic Cancellation
p.2187

A New Variable Step Size LMS Adaptive Filtering Algorithm and its Analysis
p.2193

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 605-607Research on the Optimized Algorithms on Neural...

Research on the Optimized Algorithms on Neural Network

Abstract:

In order to overcome the disadvantage of neural networks that their structure and parameters were decided stochastically or by one’s experience, an improved BP neural network training algorithm based on genetic algorithm was proposed.In this paper,genetic algorithms and simulated annealing algorithm that optimizes neural network is proposed which is used to scale the fitness function and select the proper operation according to the expected value in the course of optimization,and the weights and thresholds of the neural network is optimized. This method is applied to the stock prediction system.The experimental results show that the proposed approach have high accuracy,strong stability and improved confidence.

You might also be interested in these eBooks

Advanced Designs and Researches for Manufacturing

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 605-607)

Pages:

2175-2178

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.605-607.2175

Citation:

Cite this paper

Online since:

December 2012

Authors:

Xiao Qin Wu

Keywords:

Genetic Algorithm (GA), Neural Network (NN), Simulated Annealing (SA), Threshold, Weight

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Pan H, "Application of BP neural network based on genetic algorithm", Computer Application , 2005 , 25 (12),pp.2777-2779.

Google Scholar

[2] Kim K, "Artificial neural networks with evolutionary instance selection for financial forecasting", Expert Systems with Applications, 2006, 30,pp.519-526.

DOI: 10.1016/j.eswa.2005.10.007

Google Scholar

[3] JEONG IK, LEE JJ. Adaptive simulated annealing genetic algorithm for control application[J]. IntJ of Systems Science, 1996, 27(2 ):242 - 243.

Google Scholar

[4] Srinvas M, Patnaik L, "M,Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms", IEEE Trans on Systems , Man and Cybernetics , 1994 , 24(4),pp:162 - 167.

DOI: 10.1109/21.286385

Google Scholar

[5] LI Hongxing, HUANG Hanpang, "The Equivalence Between Fuzzy Logic Systems and Feed forward Neural networks", IEEE Trans on Neural Networks ,2000 ,11 (2) ,pp:356 - 365.

DOI: 10.1109/72.839006

Google Scholar

[6] Eric I Chang, Richard P L ippmann, "Using genetic algorithms to improve pattern classification performance", Proceedings of the 1990 Conference on advances in neural information processing systems , Denver, Colorado, United States, pp.797-803.

Google Scholar

[7] Yao X, "A review of evolutionary artificial neural networks", International Journal of Intelligent Systems. 1993, 8(4),pp: 539-567.

Google Scholar