Abstract
Techniques for prediction in spatial maps can be based on associative neural network models. Unfortunately, the performance of standard associative memories depends on the number of training patterns stored in the memory; moreover it is very sensitive to mutual correlations of the stored patterns. In order to overcome limitations imposed by processing of a large number of mutually correlated spatial patterns, we have designed the Hierarchical Associative Memory model which consists of arbitrary number of associative memories hierarchically grouped into several layers. In order to further improve its recall abilities, we have proposed new modification of our model. In this paper, we also present experimental results focused on recall ability of designed model and their analysis by means of mathematical statistics.
Chapter PDF
Similar content being viewed by others
References
Amit, D.J., Gutfreund, H., Sompolinsky, H.: Information storage in neural networks with low levels of activity. Physical Review A 35, 2293–2303 (1987)
Fukushima, K., Yamaguchi, Y., Okada, M.: Neural Network Model of Spatial Memory: Associative Recall of Maps. Neural Network 10(6), 971–979 (1997)
Hirahara, M., Oka, N., Kindo, T.: A cascade associative memory model with a hierarchical memory structure. Neural Networks 13(1), 41–50 (2000)
Hopfield, J.J.: Neural Networks and physical system with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 79, 2554–2558 (1982)
Mrázová, I., Tesková, J.: Hierarchical Associative Memories for Storing Spatial Patterns. In: Proceedings of ITAT 2002, pp. 143–154 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Štanclová, J., Zavoral, F. (2005). Hierarchical Associative Memories: The Neural Network for Prediction in Spatial Maps. In: Roli, F., Vitulano, S. (eds) Image Analysis and Processing – ICIAP 2005. ICIAP 2005. Lecture Notes in Computer Science, vol 3617. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11553595_96
Download citation
DOI: https://doi.org/10.1007/11553595_96
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28869-5
Online ISBN: 978-3-540-31866-8
eBook Packages: Computer ScienceComputer Science (R0)