Abstract
In this paper, an optimal weight semi-supervised learning machine for a single-hidden layer feedforward network (SLFN) with time delay is developed. Both input weights and output weights of the SLFN are globally optimized with manifold regularization. By feature mapping, input vectors can be placed at the prescribed positions in the feature space in the sense that the separability of all nonlinearly separable patterns can be maximized, unlabeled data can be leveraged to improve the classification accuracy when labeled data are scarce, and a high degree of recognition accuracy can be achieved with a small number of hidden nodes in the SLFN. Some simulation examples are presented to show the excellent performance of the proposed algorithm.
Similar content being viewed by others
References
M. Belkin, I. Matveeva, P. Niyogi, Regularization and semi-supervised learning on large graphs, in: Proceedings of 17th conference on learning theory (COLT), 2004.
Bishop, C. M. (1995). Neural networks for pattern recognition. New York: Oxford. University Press Inc.
Chen, Y., Xue, A. K., Lu, R. Q., & Zhou, S. S. (2008). On robustly exponential stability of uncertain neutral systems with time-varying delays and nonlinear perturbations. Nonlinear Analysis, 68, 2464–2470.
Chen, Y., Lu, R. Q., Zou, H. B., & Xue, A. K. (2014). Stability analysis for stochastic jump systems with time-varying delay. Nonlinear Analysis: Hybrid Systems, 14, 114–125.
L. Devroye, L. Gyorfi, And G. Lugosi, A probabilistic theory of pattern recognition. New York: Springer-Verlag, 1996.
Duda, R., & Hart, P. (1973). Pattern classification and scene analysis. New York: Wiley.
Huang, G. B., Zhu, Q. Y., & Siew, C. K. (Dec. 2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1–3), 489–501.
Huang, G., Song, S., Gupta, J. N. D., & Wu, C. (2014). Semi-supervised and unsupervised extreme learning machines. IEEE Transactions on Cybernetics, 44(12), 2405–2417.
Liu, J., Chen, Y., Liu, M., & Zhao, Z. (2011). SELM: semi-supervised ELM with application in sparse calibrated location estimation. Neurocomputing, 74(16), 2566–2572.
Man, Z., Lee, K., Wang, D. H., Cao, Z., & Miao, C. (2011). A new robust training algorithm for a class of single hidden layer neural networks. Neurocomputing, 74, 2491–2501.
Man, Z., Lee, K., Wang, D., Cao, Z., & Khoo, S. (2013). An optimal weight learning machine for handwritten digit image recognition. Signal Processing, 93(6), 1624–1638.
Vapnik, V. (1998). Statistical learning theory. New York: Wiley.
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. J. (1989). Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(3), 328–339.
Z. G. Wu, H. Su, J Chu, W. N. Zhou. Improved delay-dependent stability condition of discrete recurrent neural networks with time-varying delays, IEEE Transactions on Neural Networks, 21(4): 692–697, 2010.
Wu, Z. G., Lam, J., Su, H. Y., & Chu, J. (2012). Stability and dissipativity analysis of static neural networks with time delay. IEEE Transactions on Neural Networks and Learning Systems, 23(2), 199–210.
Acknowledgments
The authors thank the anonymous referee for his careful reading of the manuscript and his fruitful comments and suggestions.
Funding
This research was partially supported by Zhejiang Provincial Natural Science Foundation of China under Grant No. LY18F030003 and Science & Technology Program of Lishui City under Grant No. 2017RC01.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lu, C., Mei, Y. An Optimal Weight Semi-Supervised Learning Machine for Neural Networks with Time Delay. J Classif 37, 656–670 (2020). https://doi.org/10.1007/s00357-019-09352-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00357-019-09352-2