Abstract
In this paper, a novel mathematical model of neuron-Double Synaptic Weight Neuron (DSWN)1 is presented. The DSWN can simulate many kinds of neuron architectures, including Radial-Basis-Function (RBF), Hyper Sausage and Hyper Ellipsoid models, etc. Moreover, this new model has been implemented in the new CASSANN-II neurocomputer that can be used to form various types of neural networks with multiple mathematical models of neurons. The flexibility of the DSWN has also been described in constructing neural networks. Based on the theory of Biomimetic Pattern Recognition (BPR) and high-dimensional space covering, a recognition system of omni directionally oriented rigid objects on the horizontal surface and a face recognition system had been implemented on CASSANN-II neurocomputer. In these two special cases, the result showed DSWN neural network had great potential in pattern recognition.
This work was supported by the National Natural Science Foundation of China (No.60135010).
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Lindsey, C.S., Lindblad, T.: Review of Hardware Neural Networks: A User’s Perspective. Proceedings of the Neural Networks. From Biology to High Energy Physics, International Journal of Neural System 6(Supp.), 215–224 (1995)
Hirai, Y.: VLSI Neural Networks Systems. Proceedings of the Neural Networks. From Biology to High Energy Physics, International Journal of Neural System 6(Supp.), 203–213 (1995)
McCulloch, W.S., Pitts, W.: A logic Calculus of the Ideas Imminent in Nerves Activity. Bulletin of Mathematical Biophysics 5, 115–133 (1943)
Cohen, M.A., Grossberg, S.: Absolute Stability of Global Pattern Formation and Parallel Memory Storage by Competitive Neural Networks. IEEE Trans. Syst. Man Cybern. SMC-13, 815–826 (1983)
Hardy, R.L.: Multiquadri equations of topography and other irregular surfaces. J. Geophys, Re. 76, 1905–1915
Powell, M.J.D.: Radial basis functions for multivariable interpolation: A review. In: Mason, J.C., Cox, M.G. (eds.) Algorithms for Approximation. Clarendon Press, Oxford (1987)
Collin, D.R., Penz, P.A.: Considerations for neural network hardware implementations. In: IEEE symp. Circuit and System, pp. 834–836 (1989)
Shoujue, W., Jingpu, S., Chuan, C., Yujian, L.: Direction-Basis-Function Neural Networks. In: IJCNN 1999 (1999) (#58 Session: 4.2)
shoujue, W., Zhaozhou, L., Xiangdong, C., Bainan, W.: Discussion on the Basic Mathematical Models of Neurons in General Purpose Neurocomputer (in Chinese). Acta Electronica Sinica 29(5) 577–580 (2001)
Shoujue, W.: Biomimetic Pattern Recognition. Neural Networks Society (INNS, ENNS, JNNS) Newsletters 1(1), 3–5 (2003)
Zhihai, W., Zhanqiang, Z., Shoujue, W.: A method of biomimetic pattern recognition for face recognition (in Chinese). Pattern Recognize & Artificial Intellegence 16(4) (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Shou-jue, W., Xu, C., Hong, Q., Weijun, L., Yi, B. (2005). Double Synaptic Weight Neuron Theory and Its Application. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3610. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539087_32
Download citation
DOI: https://doi.org/10.1007/11539087_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28323-2
Online ISBN: 978-3-540-31853-8
eBook Packages: Computer ScienceComputer Science (R0)