A MULTI-VALUED NEURON WITH A PERIODIC ACTIVATION FUNCTION

Igor Aizenberg

2009

Abstract

In this paper, a new activation function for the multi-valued neuron (MVN) is presented. The MVN is a neuron with complex-valued weights and inputs/output, which are located on the unit circle. Although the MVN has a greater functionality than a sigmoidal or radial basis function neurons, it has a limited capability of learning highly nonlinear functions. A periodic activation function, which is introduced in this paper, makes it possible to learn nonlinearly separable problems and non-threshold multiple-valued functions using a single multi-valued neuron. The MVN’s functionality becomes higher and the MVN becomes more efficient in solving various classification problems. A learning algorithm based on the error-correction rule for an MVN with the introduced activation function is also presented.

References

  1. Aizenberg, N.N and Aizenberg, I.N. (1992). CNN Based on Multi-Valued Neuron as a Model of Associative Memory for Gray-Scale Images, In Proceedings of the Second IEEE Int. Workshop on Cellular Neural Networks and their Applications, Technical University Munich, 36-41
  2. Aizenberg, N.N. Ivaskiv, Yu. L., and Pospelov, D.A. (1971). About one Generalization of the Threshold Function Doklady Akademii Nauk SSSR (The Reports of the Academy of Sciences of the USSR), 196, 1287- 1290, (in Russian).
  3. Aizenberg, N.N. and Ivaskiv, Yu.L. (1977). MultipleValued Threshold Logic. Naukova Dumka Publisher House, Kiev (in Russian).
  4. Aizenberg. I.N. (1991). The Universal Logical Element over the Field of the Complex Numbers, Kibernetika (Cybernetics and Systems Analysis) 27,, 116-121 (in Russian, journal is translated into English by Consultants Bureau, An Imprint of Springer Verlag New York LLC, Vol. 27, 467-473).
  5. Aizenberg, I., Aizenberg, N., and Vandewalle, J. (2000). Multi-valued and universal binary neurons: theory, learning, applications. Kluwer Academic Publishers, Boston Dordrecht London.
  6. Aizenberg, I. and Butakoff, C. (2002). Image Processing Using Cellular Neural Networks Based on MultiValued and Universal Binary Neurons, Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 32, 169-188.
  7. Aizenberg, I., Moraga, C., and Paliy D. (2005). A Feedforward Neural Network based on Multi-Valued Neurons, In Computational Intelligence, Theory and Applications. Advances in Soft Computing, XIV, (B. Reusch - Ed.), Springer, Berlin, Heidelberg, New York, 599-612.
  8. Aizenberg, I. and Moraga, C. (2007). Multilayer Feedforward Neural Network Based on Multi-Valued Neurons (MLMVN) and a Backpropagation Learning Algorithm", Soft Computing, 11, 169-183.
  9. Aizenberg, I., Paliy, D. V., Zurada, J.M., and Astola J. T. (2008). Blur Identification by Multilayer Neural Network based on Multi-Valued Neurons, IEEE Transactions on Neural Networks, 19, 883-898.
  10. Aizenberg, I. (2008). Solving the XOR and Parity n Problems Using a Single Universal Binary Neuron, Soft Computing, 12, 215-222.
  11. Asuncion, A. and Newman, D.J. (2007). UCI Machine Learning Repository
  12. Aoki, H. and Kosugi, Y. (2000). An Image Storage System Using Complex-Valued Associative Memory, In Proceedings. of the 15th International Conference on Pattern Recognition. 2, 626-629.
  13. Aoki, H., Watanabe, E., Nagata, A., and Kosugi Y. (2001). Rotation-Invariant Image Association for Endoscopic Positional Identification Using Complex-Valued Associative Memories. In Bio-inspired Applications of Connectionism, Lecture Notes in Computer Science (Mira J., Prieto A. -eds) Springer, Berlin Heidelberg New York, 2085, 369-374.
  14. Chen, J.-H and Chen, C.-S. (2002). Fuzzy Kernel Perceptron. IEEE Transactions on Neural Networks 13, 1364-1373.
  15. Jankowski, S., Lozowski, A., and Zurada J.M. (1996). Complex-Valued Multistate Neural Associative Memory. IEEE Tranactions. on Neural Networks 7, 1491-1496.
  16. Lee, D.L. (2001). Improving the Capacity of ComplexValued Neural Networks with a Modified Gradient Descent Learning Rule IEEE Transactions on Neural Networks 12, 439-443.
  17. Lee, D.L. (2004). "Complex-valued Neural Associative Memories: Learning Algorithm and Network Stability", in book "Complex-Valued Neural Networks: Theories and Applications" (Hirose A.- Ed.), World Scientific, 29-56.
  18. Muezzinoglu, M. K., Guzelis, C., and Zurada J. M, (2003). A New Design Method for the Complex-Valued Multistate Hopfield Associative Memory, IEEE Transactions on Neural Networks 14, 891-899.
Download


Paper Citation


in Harvard Style

Aizenberg I. (2009). A MULTI-VALUED NEURON WITH A PERIODIC ACTIVATION FUNCTION . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 347-354. DOI: 10.5220/0002286203470354


in Bibtex Style

@conference{icnc09,
author={Igor Aizenberg},
title={A MULTI-VALUED NEURON WITH A PERIODIC ACTIVATION FUNCTION},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={347-354},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002286203470354},
isbn={978-989-674-014-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - A MULTI-VALUED NEURON WITH A PERIODIC ACTIVATION FUNCTION
SN - 978-989-674-014-6
AU - Aizenberg I.
PY - 2009
SP - 347
EP - 354
DO - 10.5220/0002286203470354