Abstract
Complex-valued associative memory (CAM) can store multi-level patterns. Dynamic complex-valued associative memory (DCAM) can recall all stored patterns. The CAM stores the rotated patterns, which are typical spurious states, in addition to given training patterns. So DCAM recalls all the rotated patterns in the recall process. We introduce strong bias terms to avoid recalling the rotated patterns. By computer simulations, we can see that strong bias terms can avoid recalling the rotated patterns unlike simple bias terms.
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
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the United States of America 79(8), 2554–2558 (1982)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. National Academy of Sciences of the United States of America 81(10), 3088–3092 (1984)
Jankowski, S., Lozowski, A., Zurada, J.M.: Complex-valued multistate neural sssociative memory. IEEE Transaction on Neural Networks 7(6), 1491–1496 (1996)
Kitahara, M., Kobayashi, M., Hattori, M.: Chaotic rotor associative memory. In: Proceedings of International Symposium on Nonlinear Theory and its Applications, pp. 399–402 (2009)
Lee, D.L.: Improvements of complex-valued hopfield associative memory by using generalized projection rules. IEEE Transaction on Neural Networks 17(5), 1341–1347 (2006)
Muezzinoglu, M.K., Guzelis, C., Zurada, J.M.: A new design method for the complex-valued multistate hopfield associative memory. IEEE Transaction on Neural Networks 14(4), 891–899 (2003)
Nagumo, J., Sato, S.: On a response characteristic of a mathmatical neural model. Kybernetik 10(3), 155–164 (1972)
Nakada, M., Osana, Y.: Chaotic complex-valued associative memory. In: Proc. International Symposium on Nonlinear Theory and its Applications, pp. 493–496 (2007)
Zemel, R.S., Williams, C.K.I., Mozer, M.C.: Lending direction to neural networks. Neural Networks 8(4), 503–512 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Suzuki, Y., Kitahara, M., Kobayashi, M. (2011). Dynamic Complex-Valued Associative Memory with Strong Bias Terms. In: Lu, BL., Zhang, L., Kwok, J. (eds) Neural Information Processing. ICONIP 2011. Lecture Notes in Computer Science, vol 7062. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24955-6_61
Download citation
DOI: https://doi.org/10.1007/978-3-642-24955-6_61
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24954-9
Online ISBN: 978-3-642-24955-6
eBook Packages: Computer ScienceComputer Science (R0)