Abstract
This paper proposes a complex valued generalized product neuron (GPN) which tries to incorporate polynomial structure in the aggregation of inputs. The advantage of using this model is to bring in the non-linearity in aggregation function by taking a product of linear terms in each dimension of the input space. This aggregation function has the ability to capture higher-order correlations in the input data. Such neurons are capable of learning any problem irrespective of whether the multi dimensional data is linearly separable or not which resembles higher order neurons. But these neurons do not have combinatorial increase of the number of weights in the dimensions of inputs as higher order neurons. The learning and generalization capabilities of proposed neuron are demonstrated through variety of problems. It has been shown that some benchmark problems can be solved with single GPN only without hidden layer.
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
Koch, C.: Biophysics of Computation: Information Processing in Single Neurons. Oxford University Press, Oxford (1999)
Giles, C.L., Maxwell, T.: Learning, invariance and generalization in a high-order neural network. Applied Optics 26(23), 4972–4978 (1987)
Koch, C., Poggio, T.: Multiplying with synapses and neurons, Single Neuron Computation, p. 315. Academic Press, Boston, Massachusetts (1992)
Li, D., Hirasawa, K., Hu, J., murata, J.: Multiplication units in feedforward neural networks and its training. In: Proceedings of ninth ICONIP 2002, vol. 1 (2002)
Piazza, F., Benvenuto, N.: On the complex Back propagation Algorithm. IEEE Transaction on Signal Processing 40(4), 967–969 (1992)
Box, G.E.P., Jenkins, G.M., Reinse, G.C.: Time series analysis: Forecasting and control. Prentice-Hall, Englewood Cliffs (1994)
Mackey, M., glass, L.: Oscillation and chaos in physiological control systems. Science 197, 287–289 (1997)
Schmitt, M.: On the Complexity of Computing and Learning with multiplicative Neural networks. Neural Computation 14, 241–301 (2001)
Durbin, R., rumelhart, D.E.: Product unit: A computationally powerful and biologically plausible extension to back-propagation networks. Neural Computation 1, 133–142 (1989)
Oh, S.K., Pedrycz, W., Park, B.J.: Polynomial neural networks architecture: analysis and design. In: Computers and Electrical Engineering, vol. 29, pp. 703–725. Elsevier Science, Amsterdam (2003)
Nitta, T.: An Extension of the Back-Propagation to Complex Numbers. Neural Networks 10(8), 1391–1415 (1997)
Nitta, T.: An analysis of the fundamental structure of complex-valued neurons. Neural Processing Letters 12, 239–246 (2000)
Chen, X., Li, S.: A Modified Error Function for the Complex-Value Back propagation Neural Network. Neural Information Processing 8(1) (2005)
Shin, Y., Ghosh, J.: The pi-sigma network: An efficient higher-order neural network for pattern classification and function approximation. In: Proceedings of the International Joint Conference on Neural Networks (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tripathi, B.K., Chandra, B., Kalra, P.K. (2009). The Generalized Product Neuron Model in Complex Domain. In: Köppen, M., Kasabov, N., Coghill, G. (eds) Advances in Neuro-Information Processing. ICONIP 2008. Lecture Notes in Computer Science, vol 5507. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03040-6_106
Download citation
DOI: https://doi.org/10.1007/978-3-642-03040-6_106
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03039-0
Online ISBN: 978-3-642-03040-6
eBook Packages: Computer ScienceComputer Science (R0)