Abstract
A living body has a mechanism to acquire various periodic signals in the environment. In our nerve system, this is realized by using simple neural oscillators. The oscillators optimize their internal parameters to synchronize with the external signal only from error between their own output and external signal. Furthermore, a single neural oscillator is considered to generate multiple complex signals. In this study, a simple neural oscillator model which can acquire external periodic signals is described. The proposed model is based on the multi-layered neural network with feedback connections. A task to acquire three periodic signals was applied to examine the capability of this model. As results of computer simulations, applicability and capability of this model were confirmed.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
He, J., Hashikawa, T., Ojima, H., Kinouchi, Y.: Temporal integration and duration tuning in the Dosal zone of cat auditory cortex. The Journal of Neuroscience 17(7), 2615–2625 (1997)
Furutani, N., Fujimoto, K., Akutagawa, M., Kinouchi, Y., Nagashino, H.: Mimetic Pattern Generator for Multiple Periodic signals Using Recurrent Neural Networks. In: Proceedings of Seventh International Conference on Automation, Robotics, Control and Vision, pp. 566–571 (2002)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning Internal Representations by Error Propagation. In: Rumelhart, D.E., MacCleland, J.L. (eds.) Parallel Distributed Processing, vol. 1, pp. 318–362 (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Takahashi, F., Akutagawa, M., Nagashino, H., Kinouchi, Y. (2004). A Pattern Generator for Multiple Periodic Signals Using Recurrent Neural Networks. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2004. Lecture Notes in Computer Science(), vol 3214. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30133-2_142
Download citation
DOI: https://doi.org/10.1007/978-3-540-30133-2_142
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23206-3
Online ISBN: 978-3-540-30133-2
eBook Packages: Springer Book Archive