Abstract
In this work, we give an overview of pseudoinverse learning (PIL) algorithm as well as applications. PIL algorithm is a non-gradient descent algorithm for multi-layer perception. The weight matrix of network can be exactly computed by PIL algorithm. So PIL algorithm can effectively avoid the problem of low convergence and local minima. Moreover, PIL does not require user-selected parameters, such as step size and learning rate. This algorithm has achieved good application in the fields of software reliability engineering, astronomical data analysis and so on.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lecun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems, vol. 2, pp. 396–404. Morgan Kaufman, San Francisco (1990)
Haykin, S., Deng, C.: Classification of radar clutter using neural networks. IEEE Trans. Neural Netw. 2, 589–600 (1991)
Bishop, C.M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)
Broomhead, D.S., Lowe, D.: Multivariable functional interpolation and adaptive networks. Complex Syst. 2, 321–355 (1988)
Wessels, L.F.A., Barnard, E.: Avoiding false local minima by proper initialization of connections. IEEE Trans. Neural Netw. 3, 899–905 (1992)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Guo, P., Chen, C.P., Sun, Y.: A exact supervised learning for a three-layer supervised neural network. In: Proceedings of 1995 International Conference on Neural Information Processing, pp. 1041–1044. Publishing House of Electronics Industry, Beijing (1995)
Guo, P., Lyu, M.R.: Pseudoinverse learning algorithm for feedforward neural networks. In: Advances in Neural Networks and Applications, pp. 321–326 (2001)
Guo, P., Lyu, M.R.: A pseudoinverse learning algorithm for feedforward neural networks with stacked generalization applications to software reliability growth data. Neurocomputing 56, 101–121 (2004)
Pao, Y.H., Takefuji, Y.: Functional-link net computing: theory, system architecture, and functionalities. IEEE Comput. 25, 76–79 (1992)
Pao, Y.H., Park, G.H., Sobajic, D.J.: Learning and generalization characteristics of the random vector functional-link net. Neurocomputing 6, 163–180 (1994)
Wang, D.: Editorial: randomized algorithms for training neural networks. Inf. Sci. 364–365, 126–128 (2016)
Wang, D., Li, M.: Stochastic configuration networks: fundamentals and algorithms. IEEE Trans. Cybern. 47, 3466–3479 (2017)
Scardapane, S., Wang, D.: Randomness in neural networks: an overview. WIREs Data Mining Knowl. Discov. 7 (2017)
Wang, K., Guo, P., Yin, Q., Luo, A.L., Xin, X.: A pseudoinverse incremental algorithm for fast training deep neural networks with application to spectra pattern recognition. In: 2016 International Joint Conference on Neural Networks, pp. 3453–3460. IEEE Press, New York (2016)
Wang, K., Guo, P., Xin, X., Ye, Z.: Autoencoder, low rank approximation and pseudoinverse learning algorithm. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics, pp. 948–953. IEEE Press, New York (2017)
Aggarwal, G., Gupta, D.V.: Neural network approach to measure reliability of software modules: a review. Int. J. Adv. Eng. Sci. 3, 1–7 (2013)
Zhang, X., Guo, P.: A study on software reliability prediction based on ensemble neural network (in Chinese). J. Beijing Normal Univ. (Nat. Sci.) 41, 599–603 (2005)
Mehrotra, K., Mohan, C.K., Ranka, S.: Elements of Artificial Neural Networks. MIT Press, Cambridge (1996)
Wang, G., Li, W., Xu, Y.: Research of software reliability assessment based on neural net combination model (in Chinese). Comput. Simul. 27, 176–180 (2010)
Sitte, R.: Comparison of software-reliability-growth predictions: neural networks vs parametric-recalibration. IEEE Trans. Reliab. 48, 285–291 (1999)
Wang, K., Guo, P., Luo, A.-L., Xin, X., Duan, F.: Deep neural networks with local connectivity and its application to astronomical spectral data. In: 2016 IEEE International Conference on Systems, Man, and Cybernetics, pp. 2687–2692. IEEE Press, New York (2016)
Wang, K., Guo, P., Luo, A.-L.: A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery. Mon. Not. Roy. Astron. Soc. 465, 4311–4324 (2016)
Yan, M., Yin, Q., Guo, P.: Image stitching with single-hidden layer feedforward neural networks. In: 2016 International Joint Conference on Neural Networks, pp. 4162–4169. IEEE Press, New York (2016)
Li, Y., Guo, P., Xin, X.: A divide and conquer method for automatic image annotation. In: 2016 International Conference on Computational Intelligence and Security, pp. 660–664. IEEE Press, New York (2016)
Mohammadi, M., Krishna, A., Nalesh, S., Nandy, S.: A hardware architecture for radial basis function neural network classifier. IEEE Trans. Parallel Distrib. Syst. (2017)
Li, Y., Guo, P.: Training neural networks by marginalizing out hidden layer noise. Neural Comput. Appl. (2017)
Curteanu, S., Cartwright, H.: Neural networks applied in chemistry. I. Determination of the optimal topology of multilayer perceptron neural networks. J. Chemometr. 25, 527–549 (2011)
Acknowledgements
This work is fully supported by the grants from the Joint Re-search Fund in Astronomy (Grant No. U1531242) under cooperative agreement between the National Natural Science Foundation of China (NSFC) and Chinese Academy of Sciences (CAS), Prof. Ping Guo is the author to whom all correspondence should be addressed.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Wang, J., Guo, P., Xin, X. (2018). Review of Pseudoinverse Learning Algorithm for Multilayer Neural Networks and Applications. In: Huang, T., Lv, J., Sun, C., Tuzikov, A. (eds) Advances in Neural Networks – ISNN 2018. ISNN 2018. Lecture Notes in Computer Science(), vol 10878. Springer, Cham. https://doi.org/10.1007/978-3-319-92537-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-92537-0_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92536-3
Online ISBN: 978-3-319-92537-0
eBook Packages: Computer ScienceComputer Science (R0)