Abstract
An associative memory is a special type of artificial neural network that has the purpose of store input patterns with their corresponding output patterns and efficiently recall a pattern from a noise-distorted version. Presented in this article is a new framework for constructing a binary associative memory model based on two new autoinverse operations called extended XOR/XNOR; these new operations are generated from the XOR/XNOR operations, respectively. Two types of associative memory are generated with this model: the max type (XOR-AM max), which is constructed with the maximum of the extended XOR operation, and the min type (XOR-AM min), which is constructed with the minimum of the extended XNOR operation. The XOR-AM max exhibits tolerance against the presence of patterns distorted by dilative noise, whereas the XOR-AM min exhibits tolerance against the presence of patterns distorted by erosive noise; both types of memory converge in a single step, use the same extended XOR/XNOR operator for learning and recalling phases, operate in heteroassociative and autoassociative modes, and show infinite storage capacity for the autoassociative mode. Finally, computer simulation results are presented for the new memories based on the extended XOR/XNOR (XOR-AM), which have better or equal performance compared to other associative memories. For the experiments with mixed noise, the conditions established by the kernel method proposed by Ritter for Morphological Associative Memories were conserved, and the solution algorithm proposed by Hattori for the construction of the kernel patterns of these memories was modified.
Similar content being viewed by others
References
Acevedo, M.E., Yáñez, C., López, I.: Alpha–beta bidirectional associative memories: theory and applications. Neuronal Process. Lett. 26(1), 1–40 (2007). https://doi.org/10.1007/s11063-007-9040-2
Aldape, M., Yáñez, C., Argüelles, A.J.: FPGA implementation of parallel alpha-beta associative memories. In: Campilho, A., Kamel, M. (eds.) ICIAR 2008: Image Analysis and Recognition, Lecture Notes in Computer Science, vol. 5112, pp. 1081–1090. Springer, Berlin, Heidelberg, Póvoa de Varzim, Portugal (2008). https://doi.org/10.1007/978-3-540-69812-8_108
Anderson, J.A., Rosenfeld, E.: Neurocomput. Found. Res. MIT Press, Cambridge (1988)
Chung, F.L., Lee, T.: Towards a high capacity fuzzy associative memory model. In: Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN’94), vol. 3, pp. 1595–1599. IEEE, Orlando, FL, USA (1994). https://doi.org/10.1109/ICNN.1994.374394. https://ieeexplore.ieee.org/document/374394/
Cruz, B., Sossa, H., Barrón, R.: Geometric associative processing applied to pattern classification. In: Yu, W., He, H., Zhang, N. (eds.) Advances in Neural Networks—ISNN 2009, ecture Notes in Computer Science, vol. 5552, pp. 977–985. Springer, Berlin, Heidelberg, Wuhan, China (2009). https://doi.org/10.1007/978-3-642-01510-6_111
Cuninghame-Green, R.A.: Minimax algebra. In: Beckmann, M., Künzi, H.P. (eds.) Lecture Notes in Economics and Mathematical Systems, vol. 166. Springer, Berlin (1979). https://doi.org/10.1007/978-3-642-48708-8
Feng, N., Cao, X., Li, S., Ao, L., Wang, S.: A new method of morphological associative memories. In: De-Shuang, H., Kang-Hyun, J., Hong-Hee, L., Hee-Jun, K., Vitoantonio, B. (eds.) Emerging Intelligent Computing Technology and Applications With Aspects of Artificial Intelligence. ICIC 2009, Lecture Notes in Computer Science, vol. 5755, pp. 407–416. Springer, Berlin, Heidelberg, Ulsan, South Korea (2009). https://doi.org/10.1007/978-3-642-04020-7_43. https://link.springer.com/chapter/10.1007/978-3-642-04020-7_43
Feng, N., Qiu, Y., Wang, F., Sun, Y.: A unified framework of morphological associative memories. In: Huang, D.S., Li, K., Irwin, G.W. (eds.) Intelligent Control and Automation: International Conference on Intelligent Computing, Lecture Notes in Control and Information Sciences, vol. 344, pp. 1–11. Springer Berlin Heidelberg, Berlin, Heidelberg (2006). https://doi.org/10.1007/978-3-540-37256-1_1
Feng, N., Yao, Y.: No rounding reverse fuzzy morphological associative memories. Neural Netw. World 26(6), 571–587 (2016). https://doi.org/10.14311/NNW.2016.26.033
Graña, M.: A brief review of lattice computing. In: 2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence), pp. 1777–1781. IEEE, Hong Kong, China (2008). https://doi.org/10.1109/FUZZY.2008.4630611
Graña, M.: Lattice computing: lattice theory based computational intelligence. In: Proceedings of Ibaraki Kosen Workshop MTE2008 “Mathematics, Technology and Education 2008”, pp. 1–9. Ibaraki National College of Technology, Ibaraki, Japan (2008). http://www.ehu.eus/ccwintco/uploads/a/a3/Lattice-computing-CI.pdf
Hassoun, M.H.: Associative Neural Memories: Theory and Implementation. Oxford University Press Inc, New York (1993)
Hattori, M., Fukui, A., Ito, H.: A fast method of constructing kernel patterns for morphological associative memory. In: Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP ’02, vol. 2, pp. 1058–1063. IEEE, Singapore, Singapore (2002). https://doi.org/10.1109/ICONIP.2002.1198222
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. U. S. A. 79(8), 2554–2558 (1982)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. U. S. A. 81(10), 3088–3092 (1984). https://doi.org/10.1073/pnas.81.10.3088
Junbo, F., Fan, J., Yan, S.: A learning rule for fuzzy associative memories. In: IEEE World Congress on Computational Intelligence, 1994 IEEE International Conference on Neuronal Networks, vol. 7, pp. 4273–4277. IEEE, Orlando, FL, USA (1994). https://doi.org/10.1109/ICNN.1994.374953
Kohonen, T.: Correlation matrix memories. IEEE Trans. Comput. C–21(4), 353–359 (1972). https://doi.org/10.1109/TC.1972.5008975
Kosko, B.: Fuzzy associative memories. In: Proceedings of the 2nd Joint Technology Workshop on Neural Networks and Fuzzy Logic, vol. 1, pp. 3–58. NASA, United States, California, United States (1990). https://ntrs.nasa.gov/search.jsp?R=19910012466
Liu, P.: The fuzzy associative memory of max–min fuzzy neural network with threshold. Fuzzy Sets Syst. 107(2), 147–157 (1999). https://doi.org/10.1016/S0165-0114(97)00352-7
Ritter, G.X., Sussner, P., Díaz de León, J.L.: Morphological associative memories. IEEE Trans. Neural Netw. 9(2), 281–293 (1998). https://doi.org/10.1109/72.661123
Rosen, K.H.: Discrete Mathematics and its Applications, 5th edn. Mc Graw Hill, New York (2003)
Sossa, H., Barrón, R.: Extended \(\alpha \beta\) associative memories. Revista Mexicana de Física 53(1), 10–20 (2007)
Sossa, H., Barrón, R., Cuevas, F., Aguilar, C.: Associative gray level pattern processing using binary decomposition and \(\alpha \beta\) memories. Neural Process. Lett. 22(1), 85–111 (2005). https://doi.org/10.1007/s11063-005-2902-6
Sossa, H., Barrón, R., Vázquez, R.A.: New associative memories to recall real-valued patterns. In: Sanfeliu, A., Martínez Trinidad, J.F., Carrasco Ochoa, J.A. (eds.) Progress in Pattern Recognition, Image Analysis and Applications. CIARP 2004, Lecture Notes in Computer Science, vol. 3287, pp. 195–202. Springer, Berlin, Heidelberg, Puebla, Mexico (2004). https://doi.org/10.1007/978-3-540-30463-0_24
Steinbuch, K.: Die lernmatrix. Kybernetik 1(1), 36–45 (1961). https://doi.org/10.1007/BF00293853
Sussner, P.: Observations on morphological associative memories and the kernel method. Neurocomputing 31(1–4), 167–183 (2000). https://doi.org/10.1016/S0925-2312(99)00176-9
Sussner, P., Valle, M.E.: Gray-scale morphological associative memories. IEEE Trans. Neuronal Netw. 17(3), 559–570 (2006). https://doi.org/10.1109/TNN.2006.873280
Sussner, P., Valle, M.E.: Implicative fuzzy associative memories. IEEE Trans. Fuzzy Syst. 14(6), 793–807 (2006). https://doi.org/10.1109/TFUZZ.2006.879968
Urcid, G., Ritter, G.X.: Noise masking for pattern recall using a single lattice matrix associative memory. In: Kaburlasos, V.G., Ritter, G.X. (eds.) Computational Intelligence Based on Lattice Theory, Studies in Computational Intelligence, vol. 67, pp. 81–100. Springer Berlin Heidelberg, Berlin, Heidelberg (2007). https://doi.org/10.1007/978-3-540-72687-6_5
Xiao, P., Yang, F., Yu, Y.: Max–min encoding learning algorithm for fuzzy max-multiplication associative memory networks. In: 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, vol. 4, pp. 3674–3679. IEEE, Orlando, FL, USA (1997). https://doi.org/10.1109/ICSMC.1997.633240. https://ieeexplore.ieee.org/document/633240
Yáñez, C., Díaz de León, J.L.: Associative memories based on orderings and binary operators (in Spanish). Computación y Sistemas 6(4), 300–311 (2003)
Yáñez-Márquez, C., López-Yáñez, I., Aldape-Pérez, M., Camacho-Nieto, O., Argüelles-Cruz, A.J., Villuendas-Rey, Y.: Theoretical foundations for the alpha–beta associative memories: 10 years of derived extensions, models, and applications. Neural Process. Lett. 48(2), 811–847 (2018). https://doi.org/10.1007/s11063-017-9768-2
Funding
This study is not funded by any agency.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Juan Luis Díaz de León and Arturo Gamino declares that they have no conflict of interest.
Human and animal rights
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Díaz de León, J.L., Gamino Carranza, A. New binary associative memory model based on the XOR operation. AAECC 33, 283–320 (2022). https://doi.org/10.1007/s00200-020-00446-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00200-020-00446-8