Abstract
We study a model for learning periodic signals in continouus time Hopfield networks proposed by Doya and Yoshizawa ([3]) that can be considered as a model for temporal pattern memory in animal motor systems. A network receives an external oscillatory input and adjusts its weights so that this signal can be reproduced approximately as the network output after some time. We use tools from adaptive control theory to derive an algorithm for weight matrices with special structure. If the input is generated by a network of the same structure the algorithm converges globally and does not exhibit the deficiencies of the back-propagation based approach of Doya and Yoshizawa.
Preview
Unable to display preview. Download preview PDF.
References
Albertini, F., Sontag, E. D.: For neural networks, function determines form. Neural Networks 7 (1993), 975–990
Amann, H.: Gewöhnliche Differentialgleichungen. de Gruyter, Berlin 1983
Doya, K., Yoshizawa, S.: Adaptive neural oscillator using continuous time backpropagation. Neural Networks 2 (1989), 375–385
Kosmatopolous, E. B., Christodoulou, M. A., Ioannou, P. A.: Dynamical neural network that ensure exponential identification error convergence. Neural Networks 10 (1997), 299–314
Narendra, K., Annaswamy, A.: Stable Adaptive Systems, Prentice Hall, Englewood Cliffs, New Jersey 1989
Pearlmutter, B. A.: Gradient calculations for dynamic recurrent neural networks: a survey. IEEE Trans. Neural Networks 6 (1995), 1212–1228
Reinke, R.: Adaptive Regeln zum Lernen und Reproduzieren von periodischen Signalen mit dynamischen Netzwerken. Dissertation, Universität Kaiserslautern, 1994
Sastry, S., Bodson, M.: Adaptive Control. Prentice Hall, Englewood Cliffs, New Jersey 1989
Weiß, M. G.: Learning periodic signals with neural networks. in preparation
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Georg Weiß, M. (1997). Learning oscillations using adaptive control. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020176
Download citation
DOI: https://doi.org/10.1007/BFb0020176
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive