Abstract
In this paper, we propose a weight-time-dependent (WTD) update approach for an online EM algorithm applied to the Normalized Gaussian network (NGnet). WTD aims to improve a recently proposed weight-dependent (WD) update approach by Celaya and Agostini. First, we discuss the derivation of WD from an older time-dependent (TD) update approach. Then, we consider additional aspects to improve WD, and by including them we derive the new WTD approach from TD. The difference between WD and WTD is discussed, and some experiments are conducted to demonstrate the effectiveness of the proposed approach. WTD succeeds in improving the learning performance for a function approximation task with balanced and dynamic data distributions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Celaya, E., Agostini, A.: On-line EM with weight-based forgetting. Neural Comput. 27(5), 1142–1157 (2015)
Kushner, H.J., Yin, G.G.: Stochastic Approximation Algorithms and Applications. Springer, New York (1997)
Moody, J., Darken, C.J.: Fast learning in networks of locally-tuned processing units. Neural Comput. 1(2), 281–294 (1989)
Sato, M.: Convergence of on-line EM algorithm. In: proceedings of the International Conference on Neural Information Processing, pp. 476–481 (2000)
Sato, M., Ishii, S.: On-line EM algorithm for the normalized Gaussian network. Neural Comput. 12(2), 407–432 (2000)
Xu, L., Jordan, M., Hinton, G.: An alternative model for mixtures of experts. In: Cowan, J.D., Tesauro, G., Alspector, J. (eds.) Advances in Neural Information Processing Systems, vol. 7, pp. 633–640. MIT Press, Cambridge (1995)
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
Backhus, J., Takigawa, I., Imai, H., Kudo, M., Sugimoto, M. (2016). Online EM for the Normalized Gaussian Network with Weight-Time-Dependent Updates. 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_64
Download citation
DOI: https://doi.org/10.1007/978-3-319-46681-1_64
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)