Abstract
This paper describes a robust training algorithm based on quasi-Newton process in which online and batch error functions are combined by a weighting coefficient parameter. The parameter is adjusted to ensure that the algorithm gradually changes from online to batch. Furthermore, an analogy between this algorithm and Langevin one is considered. Langevin algorithm is a gradient-based continuous optimization method incorporating Simulated Annealing concept. Neural network training is presented to demonstrate the validity of combined algorithm. The algorithm achieves more robust training and accurate generalization results than other quasi-Newton based training algorithms.
An Erratum for this chapter can be found at http://dx.doi.org/10.1007/978-3-642-33266-1_72
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Haykin, S.: Neural Networks and Learning Machines 3rd. Pearson (2009)
Zhang, Q.J., Gupta, K.C., Devabhaktuni, V.K.: Artificial neural networks for RF and microwave design-from theory to practice. IEEE Trans. Microwave Theory and Tech. 51, 1339–1350 (2003)
Ninomiya, H., Wan, S., Kabir, H., Zhang, X., Zhang, Q.J.: Robust training of microwave neural network models using combined global/local optimization techniques. In: IEEE MTT-S International Microwave Symposium (IMS) Digest, pp. 995–998 (June 2008)
Nocedal, J., Wright, S.J.: Numerical Optimization 2nd. Springer (2006)
Schraudolph, N.N., Yu, J., Gunter, S.: A stochastic quasi-Newton method for online convex optimization. In: Proc. 11th Intl. Conf. Artificial Intelligence and Statistics (2007)
Ninomiya, H.: An improved online quasi-Newton method for robust training and its application to microwave neural network models. In: Proc. IEEE&INNS/IJCNN 2010, pp. 792–799 (July 2010)
Gelfand, S.B., Mitter, S.K.: Recursive stochastic algorithms for global optimization in. Rd SIAM J. Control and Optimization 29(5), 999–1018 (1991)
Corane, A., Marechesi, M., Martini, C., Ridella, S.: Minimizing multimodal functions of continuous variables with the Simulated Annealing algorithm. ACM Trans. Math. Soft. 13(3), 262–280 (1987)
Rögnvaldsson, T.: On Langevin updating in multilayer perceptrons. Neur. Comp. 6(5), 916–926 (1991)
Kwok, T.Y., Yeung, D.Y.: Objective functions for training new hidden units in constructive neural networks. IEEE Trans. Neural Networks 8(5), 630–645 (1997)
Ma, L., Khorasani, K.: New training strategies for constructive neural networks with application to regression problems. Neural Networks 17, 589–609 (2004)
Levy, A., Montalvo, A., Gomez, S., Galderon, A.: Topics in global optimization. Lecture Notes in Mathematics, vol. (909). Springer, New York (1981)
Benoudjit, N., Archambeau, C., Lendasse, A., Leel, J., Verleysen, M.: Width optimization of the Gaussian kernels in radial basis function networks. In: Proc. Eur. Symp. Artif. Neural Netw., pp. 425–432 (April 2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ninomiya, H. (2012). Retracted: Robust Training of Feedforward Neural Networks Using Combined Online/Batch Quasi-Newton Techniques. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds) Artificial Neural Networks and Machine Learning – ICANN 2012. ICANN 2012. Lecture Notes in Computer Science, vol 7553. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33266-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-33266-1_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33265-4
Online ISBN: 978-3-642-33266-1
eBook Packages: Computer ScienceComputer Science (R0)