A novel method of neural network optimized design based on biologic mechanism

Authors:
Ding Xiaoling;Shen Jin;Fei Luo
Affiliations:
School of Computer and Electronic Engineering, Hunan University of Commerce, Changsha, China;School of Computer and Electronic Engineering, Hunan University of Commerce, Changsha, China;School of Computer, South University of Technology, Guangzhou, PRC
Venue:
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
Year:
2010

Citing 4
Cited 0

Local shape from specularity

Computer Vision, Graphics, and Image Processing
Performance Evaluation of Some Clustering Algorithms and Validity Indices

IEEE Transactions on Pattern Analysis and Machine Intelligence
An overview of evolutionary algorithms for parameter optimization

Evolutionary Computation
An accelerated learning algorithm for multilayer perceptrons: optimization layer by layer

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Optimized design of neural network based on biologic immune modulated symbiotic evolution (BIM) is proposed, which combines with the adjustment of antibody of immune modulated theory so as to keep the individual diversity With combining evolved intergrowth algorithm and density of immune principle suppress modulation mechanism together, system shortens the individual's length of code and lightened the calculating amount by solving the evolution of the colony to the neuron part, eliminates the premature convergence effectively Meanwhile, system adopts the improved immune adjustment algorithm, which improved the variety of the colony availably The neuron that produced in the colony in this way can get and realize the network quickly The results of simulation experiment which applies in system of the two stands reversing tandem cold mill show that this method is applied to the complicated climate, it has good capabilities of convergence and capability of resisting disturbance.