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.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bertotti, G.: Identification of the Damping Coefficient in Landau-Lifshitz Equation. Physical B, 102–105 (2001)
Back, T., Schwefel, H.-P.: An Overview of Algorithm for Parameter Optimization. Computation 1(1), 1–23 (1993)
Miller, R.K.: 3-D Computing: Modeling, Image Processing, and Noneross. GA: SEAI Visualization Technical (1992)
Hearly, G., Binford, T.: IOCAL Shape Form Speculating. Compute. Vis. Graph. Image Process. 42, 62–86 (1988)
Dillenbourg, J.: A Self: A Computational Approach to Distributed Cognition. European Journal of Psychology Education 7(4), 252–373 (1992)
Maulik, U., Bandyopdhyay, S.: Performance Evaluation of Some Clustering Algorithms and Validity Indices. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1650–1654 (2002)
Jiang, W.J., Wang, P.: Research on Distributed Solution and Correspond Consequence of Complex System Based on MAS. Journal of Computer Research and Development 43(9), 1615–1623 (2006)
Erg zinger, S., Thomsen, E.: An Accelerated Learning Algorithm for Mrltilayer Percephons: Optimization Layer by Layer. IEEE Trans. Neural Networks 6, 31–42 (1995)
He, Y.B., Li, X.Z.: Application of Control Technology Based on Neural Networks. Science Press, Beijing (2000)
Jiang, W.J.: Research on the Learning Algorithm of BP Neural Networks Embedded in Evolution Strategies. In: WCICA 2005, pp. 222–227 (2005)
Jiang, W.J., Pu, W., Lianmei, Z.: Research on Grid Resource Scheduling Algorithm Based on MAS Cooperative Bidding Game. Chinese Science F 52(8), 1302–1320 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xiaoling, D., Jin, S., Luo, F. (2010). A Novel Method of Neural Network Optimized Design Based on Biologic Mechanism. In: Zhang, L., Lu, BL., Kwok, J. (eds) Advances in Neural Networks - ISNN 2010. ISNN 2010. Lecture Notes in Computer Science, vol 6063. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13278-0_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-13278-0_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13277-3
Online ISBN: 978-3-642-13278-0
eBook Packages: Computer ScienceComputer Science (R0)