Training algorithm for perceptron with multi-pulse type activation function

  • Zisheng Wu
  • Bingo Wing-Kuen LingEmail author
Original Paper


The conventional perceptron with the sign type activation function can be used for performing the linearly separable pattern recognition with its weight vector being found by the conventional perceptron training algorithm. On the other hand, the perceptron with the multi-pulse type activation function can be used for performing the piecewise linearly separable pattern recognition. This paper proposes a training algorithm for finding its weight vector. Moreover, some application examples of this perceptron are given for the demonstration purpose.


Piecewise linearly separable pattern recognition Perceptron training algorithm Perceptron with the multi-pulse type activation function 



This paper was supported partly by the National Nature Science Foundation of China (Nos. U1701266, 61372173 and 61671163), the Team Project of the Education Ministry of the Guangdong Province (No. 2017KCXTD011), the Guangdong Higher Education Engineering Technology Research Center for Big Data on Manufacturing Knowledge Patent (No. 501130144) and Hong Kong Innovation and Technology Commission, Enterprise Support Scheme (No. S/E/070/17).


  1. 1.
    Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386–408 (1958)CrossRefGoogle Scholar
  2. 2.
    Novikoff, A.: On the convergence proofs on perceptrons. Proc. Symp. Math. Theory Autom. 12, 615–622 (1962)MathSciNetGoogle Scholar
  3. 3.
    Minsky, M.L., Papert, S.A.: Perceptrons. MIT Press, London (1969)zbMATHGoogle Scholar
  4. 4.
    Gallant, S.I.: Perceptron-based learning algorithms. IEEE Trans. Neural Netw. 1(2), 179–191 (1990)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Freund, Y., Schapire. R.E.: Large margin classification using the perceptron algorithm. In: Proceedings of the 11th Annual Conference on Computational Learning Theory. ACM Press (1998)Google Scholar
  6. 6.
    Li, Y.Y., Zaragoza, H., Herbrich, R., Shawe-Taylor, J., Kandola, J.: The perceptron algorithm with uneven margins. In: Proceedings of the 19th International Conference on Machine Learning, pp. 379-386 (2002)Google Scholar
  7. 7.
    Wan, S.J.: Cone algorithm: an extension of the perceptron algorithm. IEEE Trans. Syst. Man Cybern. 24(10), 1571–1576 (1994)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Widrow, B., Lehr, M.A.: 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. Proc. IEEE 78(9), 1415–1442 (1990)CrossRefGoogle Scholar
  9. 9.
    Greenwood, G.W.: Training multiple-layer perceptrons to recognize attractors. IEEE Trans. Evol. Comput. 1(4), 244–248 (1997)CrossRefGoogle Scholar
  10. 10.
    Gurney, K.: An introduction to neural networks. UCL Press, London (1997)CrossRefGoogle Scholar
  11. 11.
    Gas, B.: Self-organizing multilayer perceptron. IEEE Trans. Neural Netw. 21(11), 1766–1779 (2010)CrossRefGoogle Scholar
  12. 12.
    Li, Y.Z., Zhang, Y., Li, W., Jiang, T.: Marine wireless big data: efficient transmission, related applications, and challenges. IEEE Wirel. Commun. 25(1), 19–25 (2018)CrossRefGoogle Scholar
  13. 13.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  14. 14.
    Chen, F.Y., Chen, G.R., He, G.L., Xu, X.B., He, Q.B.: Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations. IEEE Trans. Neural Networks 20(10), 1645–1658 (2009)CrossRefGoogle Scholar
  15. 15.
    Chen, F.Y., Chen, G.R., He, Q.B., He, G.L., Xu, X.B.: Universal perceptron and DNA-like learning algorithm for binary neural networks: non-LSBF implementations. IEEE Trans. Neural Netw. 20(8), 1293–1301 (2009)CrossRefGoogle Scholar
  16. 16.
    Chen, F.Y., Tang, W.H., Chen, G.R.: Single-layer perceptron and dynamic neuron implementing linearly non-separable Boolean functions. Int. J. Circuit Theory Appl. 37(3), 433–451 (2009)CrossRefGoogle Scholar
  17. 17.
    Czerniak, J., Zarzycki, H: Application of rough sets in the presumptive diagnosis of urinary system diseases. In: Artificial Intelligence and Security in Computing Systems, pp. 41–51 (2003)CrossRefGoogle Scholar
  18. 18.
    Li, Y., Ling, B.W.K., Xie, L.X., Dai, Q.Y.: Using LASSO for formulating constraint of least-squares programming for solving one-norm equality constrained problem. SIViP 11, 179–186 (2017)CrossRefGoogle Scholar
  19. 19.
    Li, Y.Z., Xie, P.C., Tang, Z.S., Jiang, T., Qi, P.H.: SVM-based sea-surface small target detection: a false-alarm-rate-controllable approach. IEEE Geosci. Remote Sens. Lett. 16(8), 1225–1229 (2019)CrossRefGoogle Scholar
  20. 20.
    Abid, F.B., Zgarni, S., Braham, A.: Distinct bearing faults detection in induction motor by a hybrid optimized SWPT and aiNet-DAG SVM. IEEE Trans. Energy Convers. 33(4), 1692–1699 (2018)CrossRefGoogle Scholar
  21. 21.
    Ho, C.Y.F., Ling, B.W.K., Lam, H.K., Nasir, M.H.U.: Global convergence and limit cycle behavior of weights of perceptron. IEEE Trans. Neural Networks 19(6), 938–947 (2008)CrossRefGoogle Scholar
  22. 22.
    Fu, X.G., Li, S.H., Fairbank, M., Wunsch, D.C.: Training recurrent neural networks with the Levenberg–Marquardt algorithm for optimal control of a grid-connected converter. IEEE Trans. Neural Netw. Learn. Syst. 19(9), 1900–1912 (2015)MathSciNetCrossRefGoogle Scholar
  23. 23.
  24. 24.
    Zhao, Y., Deng, B., Wang, Z.: Analysis and study of perceptron to solve XOR problem. In: The 2nd International Workshop on Autonomous Decentralized System, pp. 168–173 (2002)Google Scholar
  25. 25.
    Maimaitiyiming, M., Sagan, V., Sidike, P., Kwasniewski, M.T.: Dual activation function-based extreme learning machine (ELM) for estimating Grapevine berry yield and quality. Remote Sens. 11, 7 (2019)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2020

Authors and Affiliations

  1. 1.School of Information EngineeringGuangdong University of TechnologyGuangzhouChina

Personalised recommendations