Abstract
The recurrent associative memory networks with complex-valued Hebbian matrices of connections are designed from interacting limit-cycle oscillators. These oscillatory networks have peculiarities and advantages as compared to Hoplield neural network model. In particular, the class of networks with high memory characteristics (the capacity close to 1, low extraneous memory) exists. At zero values of oscillator frequencies the designed networks are closely related to the known “clock” neural networks (networks from complex-valued neurons). Pattern recognition of colored images and recognition of objects with complicated topological structure look quite natural in the context of such models. Exact solutions have been obtained for a few types of the networks considered, in particular, for homogeneous closes chains.
Preview
Unable to display preview. Download preview PDF.
References.
Sompolinsky H., Tsodyks M., Processing of sensory information by a network of oscillators with memory,-Intern. J. of Neural Systems, v.3, Suppl., 1992, pp.51–56.
Kuramoto Y., Aoyagi T., Nishikawa L, Chawanya T., Okuda K. Neural network model carrying phase information,-Progr. Theor. Phys., v.37, n.5, 1992, pp. 1113–1126.
Vicente C.J.P., Arenas A., Bonilla L.L., On the short-time dynamics of networks of Hebbian coupled oscillators,-J. Phys. A, v.29, Iss.1, 1996, pp. L9–L16.
Kuzmina M. G., Manykin E. A., Surina I. L, Oscillatory networks with Hebbian matrix of connections — Led. Notes in Comp. Sci., v.930, Proc. of IWANN'95, 1995, pp.246–251.
Kuzmina M. G., Manykin E. A., Surina I. L, Oscillatory networks with guaranteed memory characteristics,-Proc. of EUFIT'96, v.1, 1996, pp.320–324.
Kuzmina M. G., Manykin E. A., Surina I. L, Oscillatory networks of associative memory-Optical Memory and NN, v.5, n.2, 1996, pp.91–103.
Matthews P.C., Strogatz S.H., Phase diagram for collective behavior of limit-cycle oscillators,-Phys. Rev. Lett., v.65, n.14, 1990, pp.1701–1704.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kuzmina, M., Manykin, E., Surina, I. (1997). Recurrent associative memory network of nonlinear coupled oscillators. 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/BFb0020193
Download citation
DOI: https://doi.org/10.1007/BFb0020193
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