Abstract
Sensitive dependance on initial conditons is studied for a diluted and non symmetric model of neural networks. Two parameters appear to be relevant: the connectivity which allows local difference to spread all over the network and the noise temperature which smooths these difference. Their influence is shown by theoretical estimations in the thermodynamic limit and by simulations which give exactly the same results for medium size networks: when the connectivity reaches a critical threshold, transition from a “sensitive” dynamic to a single attractor dynamic is exhibited for a critical temperature which can be computed. This result is proved first for constant connectivity models then for randomly diluted models.
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
DERRIDA, POMMEAU. Random Networks of Automata: A simple Annealed Approximation. Europhys.Lett, 1, (2), 44–49 (1987)
DERRIDA, WEISBUCH. Evolution of Overlaps between configurations in Random Boolean Networks. J.Phys (Paris), 47 (1986)1297.
DERRIDA, WEISBUCH. Europhys.Lett, 4,(1987).
DERRIDA, GARDNER, Zippelius. An exactly Solvable Asymmetric Neural Network Model. Europhys.Lett, 4,(2),(1987)
BAUER, MARTIENSTEN. Quasy_Periodicity Route to chaos in Neural Networks. Europhys.Lett, 10,(5), (1989)
K.E. KURTEN. Phase transitions in quasirandom neural networks,IJCNN San Diego 1988
PERETTO, NIEZ. Stochastic dynamic of Neural Networks. IEEE Trans Man Cybern 16. 1 (1986)
C.A. SKARDA, W.J. FREEMAN.How brains make chaos in order to make sense of the world. Behavioral and Brain Sciences (10),161–195 (1987)
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Benaim, M., Samuelides, M. (1990). Emergence of Complexity in the Dynamic of a Diluted Neural Network. In: International Neural Network Conference. Springer, Dordrecht. https://doi.org/10.1007/978-94-009-0643-3_140
Download citation
DOI: https://doi.org/10.1007/978-94-009-0643-3_140
Publisher Name: Springer, Dordrecht
Print ISBN: 978-0-7923-0831-7
Online ISBN: 978-94-009-0643-3
eBook Packages: Springer Book Archive