Abstract
The macroscopic dynamics of an extremely diluted three-state neural network based on mutual information and mean-field theory arguments is studied in order to establish the stability of the stationary states. Results are presented in terms of the pattern-recognition overlap, the neural activity, and the activity-overlap. It is shown that the presence of synaptic noise is essential for the stability of states that recognize only the active patterns when the full structure of the patterns is not recognizable. Basins of attraction of considerable size are obtained in all cases for a not too large storage ratio of patterns.
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
D. Dominguez and E. Korutcheva, Three-state neural network: From mutual Information to the Hamiltonian. Phys.Rev.E 62(2), (2000) 2620–2628.
C.E. Shannon, A Mathematical Theory of Communication, The Bell System Technical Journal, 27, (1948).
R.E. Blahut, Principles and Practice of Information Theory, Addison-Wesley, Reading, MA, (1990), Chapter 5.
D. Dominguez and D. Bollé, Self-control in Sparsely Coded Networks. Phys.Rev.Lett. 80(13), (1998) 2961–2964.
D. Bollé, D. Dominguez and S. Amari, Mutual Information of Sparsely-Coded Associative Memory with Self-Control and Ternary Neurons. Neural Networks 13(4-5), (2000) 455–462.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dominguez, D.R.C., Korutcheva, E., Theumann, W.K., Erichsen, R. (2002). Flow Diagrams of the Quadratic Neural Network. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_22
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_22
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive