Abstract
We investigate attractor neural networks with a modular structure, where a local winner-takes-all rule acts within the modules (called hypercolumns). We make a signal-to-noise analysis of storage capacity and noise tolerance, and compare the results with those from simulations. Introducing local winner-takes-all dynamics improves storage capacity and noise tolerance, while the optimal size of the hypercolumns depends on network size and noise level.
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.
Similar content being viewed by others
References
Hubel, D.H. and T.N. Wiesel: Uniformity of monkey striate cortex: A parallel relationship between field size, scatter and magnification factor. J. Comp. Neurol., 1974(158): p. 295–306.
Holst, A. and A. Lansner: A Higher Order Bayesian Neural Network for Classification and Diagnosis, in Applied Decision Technologies: Computational Learning and Probabilistic Reasoning, A. Gammerman, Editor. 1996, John Wiley & Sons Ltd.: New York. p. 251–260.
Lansner, A. and Ö. Ekeberg: A one-layer feedback artificial neural network with a Bayesian learning rule. Int. J. Neural Systems, 1989. Vol. 1: p. 77–87.
Sandberg, A., et al.: A Bayesian attractor network with incremental learning. to appear in Network: Computation in Neural Systems, 2002. Vol. 13(2).
Ström, B.: A Model of Neocortical Memory, Using Hypercolumns and a Bayesian Learning Rule. 2000, Nada, KTH: Stockholm.
Peterson, C. and B. Söderberg: A New Method for Mapping Optimization Promlems onto Neural Networks. International Journal of Neural Systems, 1989. Vol. 1(3).
Levy, N., D. Horn, and E. Ruppin: Associative Memory in a Multi-modular Network. Neural Computation, 1999. Vol. 11: p. 1717–1737.
O’Kane, D. and A. Treves: Short-and long-range connections in autoassociative memory. J. Phys. A, 1992. Vol. 25: p. 5055–5069.
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
Johansson, C., Sandberg, A., Lansner, A. (2002). Attractor Neural Networks with Hypercolumns. 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_32
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_32
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