Abstract
This paper addresses quantitative techniques for the design and characterization of artificial neural networks based on Chaotic Neural Nodes, Recursive Processing Elements, and Bifurcation Neurons. Such architectures can be programmed to store cyclic patterns, having as important applications spatio temporal processing and computation with non fixed-point attractors. The paper also addresses the performance measurement of associative memories based on Recursive Processing Elements, considering situations of analog and digital noise in the prompting patterns, and evaluating how this noise reflects in the Hamming distance between the desired stored pattern and the answer pattern produced by the neural network.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
K. Aihara et al. Chaotic Neural Networks, Physica Letters A, v. 144 p. 333, 1990
K. Kaneko, The Coupled Map Lattice: Introduction, Phenomenology, Lyapunov Analysis, Thermodynamics and Applications, in Theory and Applications of Coupled Map Lattices, John Wiley Sons, 1993
E. Del Moral Hernandez, Artificial Neural Networks Based on Bifurcating Recursive Processing Elements, UMI Dissertation Services, Ann Arbor, MI, 1998
N. H. Farhat et al. Complexity and Chaotic Dynamics in Spiking Neuron Embodiment, in Adaptive Computing, Mathematics, Electronics, and Optics, SPIE Critical Review, v. CR55 p. 77, 1994
N. H. Farhat and E. Del Moral Hernandez, Logistic Networks with DNA-Like Encoding and Interactions, in Lecture Notes in Computer Science, v. 930 p. 214, Springer Verlag, 1995
E. Del Moral Hernandez, Bifurcating Pulsed Neural Networks, Chaotic Neural Networks and Parametric Recursions, IJCNN2000, IEEE, 2000
S. Haykin, Neural Networks: a Comprehensive Foundation, Prentice Hall, 1999
R. C. Hilborn, Chaos and Nonlinear Dynamics, Oxford U. Press, 1994
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Del Moral Hernandez, E. (2001). Studying Neural Networks of Bifurcating Recursive Processing Elements — Quantitative Methods for Architecture Design. In: Mira, J., Prieto, A. (eds) Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. IWANN 2001. Lecture Notes in Computer Science, vol 2084. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45720-8_65
Download citation
DOI: https://doi.org/10.1007/3-540-45720-8_65
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42235-8
Online ISBN: 978-3-540-45720-6
eBook Packages: Springer Book Archive