Abstract
We show how to build accurately a continuous-time recurrent neural network architecture that implements the discriminating functions for a gaussian mixture. The network structure is obtained in batch after the distribution parameters have been estimated using the EM algorithm. Simulations show that the neural network at steady state is capable of being an accurate estimator for the posterior probabilities.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dempster, A. P., Laird, N. M., and Rubin, D. B. (1977). “Maximum likelihood from incomplete data via the EM algorithm”. Jornal of the Royal Statistical Society, B39, pp. 1–38.
Jordan, M. I., Jacobs, R.A. (1994). “Hierarchical mixtures of experts and the EM algorithm”. Neural Computation, 6, pp. 181–214.
Kohonen, T. (1990). “The self organizing map”. Proceedings of the IEEE, 78, pp. 1464–1480.
Marcus, M. C., Westervelt, R. M. (1989) “Dynamics of iterated map neural networks”. Physical Review A, 40, pp. 501–504.
Redner, R. A., and Walker, H. F. (1984). “Mixture densities, maximum likelihood and the EM algorithm”. SIAM Review, 26, pp. 195–239.
Waugh, F. R., and Westervelt, R. M. (1993). “Analog neural networks with local competition. I. Dynamics and stability”. Physical Review E, 47, pp. 4524–4536.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London Limited
About this paper
Cite this paper
Budillon, A., Corrente, M., Palmieri, F. (1998). EM Algorithm: A Neural Network View. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets WIRN VIETRI-97. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1520-5_29
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1520-5_29
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1522-9
Online ISBN: 978-1-4471-1520-5
eBook Packages: Springer Book Archive