Abstract
A single hidden layer neural networks (SHLNNs) learning algorithm has been proposed which is called Extreme Learning Machine (ELM). It shows extremely faster than typical back propagation (BP) neural networks based on gradient descent method. However, it requires many more hidden neurons than BP neural networks to achieve assortive classification accuracy. This then leads more test time which plays an important role in practice. A novel learning algorithm (USA) for SHLNNs has been presented which updates the weights by using gradient method in the ELM framework. In this paper, we employ the conjugate gradient method to train the SHLNNs on the MNIST digit recognition problem. The simulated experiment demonstrates the better generalization and less required hidden neurons than the common ELM and USA.
J. Wang—This work was supported in part by the National Natural Science Foundation of China (No. 61305075), the China Postdoctoral Science Foundation (No. 2012M520624), the Natural Science Foundation of Shandong Province (No. ZR2013FQ004, ZR2013DM015), the Specialized Research Fund for the Doctoral Program of Higher Education of China (No. 20130133120014) and the Fundamental Research Funds for the Central Universities (No. 13CX05016A, 14CX05042A, 15CX05053A, 15CX08011A).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(123), 489–501 (2006)
Serre, D.: Matrices: Theory and Applications. Springer, New York (2002)
Rao, C.R., Mitra, S.K.: Generalized Inverse of Matrices and Its Applications. Wiley, New York (1971)
Zhang, P., Wang, X., Gu, D., Zhao, S.: Extreme learning machine based on conjugate gradient. J. Comput. Appl. 35(10), 2757–2760 (2015)
Chorowski, J., Wang, J., Zurada, J.M.: Review and performance comparison of SVM- and ELM-based classifiers. Neurocomputing 128(5), 507–516 (2014)
Bartlett, P.L.: The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE Trans. Inf. Theor. 44(2), 525–536 (1998)
Widrow, B., Greenblatt, A., Kim, Y., Park, D.: The no-prop algorithm: a new learning algorithm for multilayer neural networks. Neural Netw. 37, 182–188 (2013)
Zhu, Q.Y., Qin, A.K., Suganthan, P.N., Huang, G.B.: Evolutionary extreme learning machine. Pattern Recogn. 38(10), 1759–1763 (2005)
Yu, D., Deng, L.: Efficient and effective algorithms for training single-hidden-layer neural networks. Pattern Recogn. Lett. 33(5), 554–558 (2012)
Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Netw. 4(2), 251–257 (1991)
Leshno, M., Lin, V.Y., Pinkus, A., Schocken, S.: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Netw. 6(6), 861–867 (1993)
Huang, G.B., Babri, H.A.: Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions. IEEE Trans. Neural Netw. 9(1), 224–229 (1998)
Huang, G.B.: Learning capability and storage capacity of two hidden-layer feedforward networks. IEEE Trans. Neural Netw. 14(2), 274–281 (2003)
Fletcher, R., Reeves, C.M.: Function minimization by conjugate gradients. Comput. J. 7, 149–154 (1964)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Gong, X., Wang, J., Wang, Y., Zurada, J.M. (2016). A Conjugate Gradient-Based Efficient Algorithm for Training Single-Hidden-Layer Neural Networks. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9950. Springer, Cham. https://doi.org/10.1007/978-3-319-46681-1_56
Download citation
DOI: https://doi.org/10.1007/978-3-319-46681-1_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46680-4
Online ISBN: 978-3-319-46681-1
eBook Packages: Computer ScienceComputer Science (R0)