Abstract
Pattern reconstruction or pattern restoration in the presence of noise is a main problem in pattern recognition. An essential feature of the noise acting on a pattern is its local nature. If a pattern is split into enough sub-patterns, a few of them will be less or more affected by noise, others will remain intact. In this paper, we propose a simple but effective methodology that exploits this fact for the efficient restoration of a pattern. A pattern is restored if enough of its sub-patterns are also restored. Since several patterns can share the same sub-patterns, the final decision is accomplished by means of a voting mechanism. Before deciding if a sub-pattern belongs to a pattern, sub-pattern restoration in the presence of noise is done by an associative memory. Numerical and real examples are given to show the effectiveness of the proposal. Formal conditions under which the proposal guaranties perfect restoration of a pattern from an unaltered or and altered version of it are also given.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Steinbuch K. (1961). die Lernmatrix. Kyberneitk C-1(1): 26–45
Anderson J. (1972) A simple neural network generating an interactive memory. Mathematical Biosciences C-14: 197–220
Kohonen T. (1972) Correlation matrix memories. IEEE Transactions Computers C-21(4): 444–445
Palm G. (1982) Neural Assemblies. An alternative Approach to Artificial Intelligence. Studies of the Brain function. Springer Verlag, Berlin
Hopfield J. (1982) Neural network and physicals systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences C-79: 2554–2558
Ritter G.X. et al. (1998) Morphological associative memories. IEEE Transactions on Neural Networks, C-9: 281–293
Ritter G.X. et al. (1999) Morphological bi-directional associative memories. Neural Networks. 12: 851–867
Yáñez, C.: Associative memories based on order relations and binary operators (In Spanish), PhD Thesis, Center for Computing Research-IPN, 2002.
Ritter G.X. et al.: Reconstruction of patterns from noisy inputs using morphological associative memories. International Journal of Mathematical Imaging and Vision. 19(2): 95–111
Sossa H. et al. (2004) Extended associative memories for recalling gray level patterns, Lecture Notes on Computer Science, Vol. 3287. Springer Verlag, Berlin, pp. 187–194
Sossa H. et al. (2004) New Associative Memories to Recall Real-Valued Patterns, LNCS. Vol. 3287. Springer Verlag, Berlin, pp. 195–202
Sossa H. et al. (2005). Associative gray-level pattern processing using binary decomposition and a-b memories. Neural Processing Letters 22: 85–111
Hassouon M.H. (1993) Associated Neural Memories. Theory and Implementation. Oxford University Press, Oxford
Lee D.D., Seung H.S. (1999) Learning the parts of objects by non-negative matrix factorisation. Nature 401: 788–791
Ikeda N., Watta P., Artiklar M., Hassoun M. (2001) A Two-level hamming network for high performance associative memory. Neural Networks. 14: 1189–1200
Watta P., Hassoun M. (2001) Generalizations of the hamming associative memory. Neural Processing Letters 13(2): 183–194
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cruz, B., Sossa, H. & Barrón, R. A New Two-Level Associative Memory for Efficient Pattern Restoration. Neural Process Lett 25, 1–16 (2007). https://doi.org/10.1007/s11063-006-9026-5
Received:
Accepted:
Published:
Issue date:
DOI: https://doi.org/10.1007/s11063-006-9026-5