Abstract
We propose a Spatial Artificial Neural Network (SANN) with spatial architecture which consists of a multilayer feedforward neural network with hidden units adopt recurrent lateral inhibition connection, all input and hidden neurons have synapses connections with the output neurons. In addition, a supervised learning algorithm based on error back propagation is developed. The proposed network has shown a superior generalization capability in simulations with pattern recognition and non-linear function approximation problems. And, the experimental also shown that SANN has the capability of avoiding local minima problem.
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
McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5, 115–433 (1943)
Anders, K.: What are Artificial Neural Networks? Nature Biothechnology 26, 195–197 (2008)
Stamatis, N., Parthimos, D., Griffith, T.M.: Forecasting chaotic cardiovascular time series with an adaptive slope multilayer perceptron neural network. IEEE Transactions on Biomedical Engineering 46(12), 144–153 (1999)
Li, Z., Melek, W.W.: Neural network-based prediction of cardiovascular response due to the gravitational effects. Control and Intelligent Systems 36(1), 81–91 (2008)
Liu, D., Ju, C.: Application of an improved BP neural network in business forecasting. In: Sixth World Congress on Intelligent Control and Automation, p. 5 (2006)
Pan, W.-T., Lin, W.-Y.: Use probabilistic neural network to construct early warning model for business financial distress. In: 2008 International Conference on Management Science and Engineering (ICMSE), pp. 134–139 (2008)
Pan, W.-T.: Use of probabilistic neural network to construct early warning model for business financial distress. Journal of Statistics and Management Systems 11(4), 749–760 (2008)
Cheng, M.-Y., Tsai, H.-C., Sudjono, E.: Conceptual cost estimates using evolutionary fuzzy hybrid neural network for projects in construction industry. Expert Systems with Applications 37(6), 4224–4231 (2010)
Chao, J., Hoshino, M., Kitamura, T.: A New Pyramid Network and Its Generalization Performance. In: Proc. of IJCNN 2001: International Joint Conference on Neural Networks, Washington D.C., pp. 2811–2816 (2001)
Jaeger, H., Haas, H.: Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science 304, 78–80 (2004)
Buzsáki, G.: The structure of consciousness. Nature 446, 267 (2007)
Sa, L., Kil, R.M.: A Gaussian potential function network with hierarchnically self-organization learning. Neural Networks 4, 207–224 (1991)
Simon, W.E., Carter, J.R.: Back propagation learning equations from the minimization of the recursive error. In: IEEE International Conference on Systems Engineering, pp. 155–160 (1989)
Jain, L.C.: Hybrid Connectionist Systems in Research and Teaching. IEEE Aerospace and Electronic Systems Magazine 10(3), 14–18 (1995)
Li, A.-J., Liu, Y.-H., Luo, S.-W.: On the solution of the XOR problem using the decision tree-based neural network. In: International Conference on Machine Learning and Cybernetics, vol. 2, pp. 1048–1052 (2003)
Barmann, F., Biegler-Konig, F.: On a class of efficient learning algorithms for neural networks. Neural Networks 5, 139–144 (1992)
Gad, E.F., Atiya, A.F., Shaheen, S., El-Dessouki, A.: A new algorithm for learning in piecewise-linear neural networks. Neural Networks 13, 485–505 (2000)
Wen, C., Ma, X.: A max-piecewise-linear neural network for function approximation. Neurocomputing 71(4-6), 843–852 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yang, G., Qiao, J., Yuan, M. (2011). A Novel Spatial Architecture Artificial Neural Network Based on Multilayer Feedforward Network with Mutual Inhibition among Hidden Units. In: Liu, D., Zhang, H., Polycarpou, M., Alippi, C., He, H. (eds) Advances in Neural Networks – ISNN 2011. ISNN 2011. Lecture Notes in Computer Science, vol 6675. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21105-8_57
Download citation
DOI: https://doi.org/10.1007/978-3-642-21105-8_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21104-1
Online ISBN: 978-3-642-21105-8
eBook Packages: Computer ScienceComputer Science (R0)