Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Granular Bidirectional and Multidirectional Associative Memories: Towards a Collaborative Buildup of Granular Mappings

  • Pedrycz, Witold (Dept. of Electrical & Computer Engineering University of Alberta Edmonton, Dept. of Electrical and Computer Engineering Faculty of Engineering, King Abdulaziz University Jeddah, Systems Research Institute, Polish Academy of Sciences Warsaw)
  • Received : 2017.04.17
  • Accepted : 2017.05.15
  • Published : 2017.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Associative and bidirectional associative memories are examples of associative structures studied intensively in the literature. The underlying idea is to realize associative mapping so that the recall processes (one-directional and bidirectional ones) are realized with minimal recall errors. Associative and fuzzy associative memories have been studied in numerous areas yielding efficient applications for image recall and enhancements and fuzzy controllers, which can be regarded as one-directional associative memories. In this study, we revisit and augment the concept of associative memories by offering some new design insights where the corresponding mappings are realized on the basis of a related collection of landmarks (prototypes) over which an associative mapping becomes spanned. In light of the bidirectional character of mappings, we have developed an augmentation of the existing fuzzy clustering (fuzzy c-means, FCM) in the form of a so-called collaborative fuzzy clustering. Here, an interaction in the formation of prototypes is optimized so that the bidirectional recall errors can be minimized. Furthermore, we generalized the mapping into its granular version in which numeric prototypes that are formed through the clustering process are made granular so that the quality of the recall can be quantified. We propose several scenarios in which the allocation of information granularity is aimed at the optimization of the characteristics of recalled results (information granules) that are quantified in terms of coverage and specificity. We also introduce various architectural augmentations of the associative structures.

Keywords

References

  1. E. K. Bridger, A. L. Kursawe, R. Bader, R. Tibon, N. Gronau, D. A. Levy, and A. Mecklinger, "Age effects on associative memory for novel picture pairings," Brain Research, vol. 1664, pp. 102-115, 2017. https://doi.org/10.1016/j.brainres.2017.03.031
  2. G. Palm, "On associative memory," Biological Cybernetics, vol. 36, no. 1, pp. 19-31, 1980. https://doi.org/10.1007/BF00337019
  3. G. Palm, "Neural associative memories and sparse coding," Neural Networks, vol. 37, pp. 165-171, 2013. https://doi.org/10.1016/j.neunet.2012.08.013
  4. R. Belohlavek, "Fuzzy logical bidirectional associative memory," Information Sciences, vol. 128, no. 1, pp. 91-103, 2000. https://doi.org/10.1016/S0020-0255(00)00044-X
  5. B. Kosko, "Bidirectional associative memories," IEEE Transactions on Systems, Man, and Cybernetics, vol. 18, no. 1, pp. 49-60, 1988. https://doi.org/10.1109/21.87054
  6. M. E. Valle and P. Sussner, "Storage and recall capabilities of fuzzy morphological associative memories with adjunction-based learning," Neural Networks, vol. 24, no. 1, pp. 75-90, 2011. https://doi.org/10.1016/j.neunet.2010.08.013
  7. Q. Cheng and Z. T. Fan, "The stability problem for fuzzy bidirectional associative memories," Fuzzy Sets and Systems, vol. 132, no. 1, pp. 83-90, 2002. https://doi.org/10.1016/S0165-0114(01)00165-8
  8. E. Esmi, P. Sussner, and S. Sandri, "Tunable equivalence fuzzy associative memories," Fuzzy Sets and Systems, vol. 292, pp. 242-260, 2016. https://doi.org/10.1016/j.fss.2015.04.004
  9. W. Feng, S. X. Yang, H. Wu, "Further results on robust stability of bidirectional associative memory neural networks with norm-bounded uncertainties," Neurocomputing, vol. 148, pp. 535-543, 2015. https://doi.org/10.1016/j.neucom.2014.07.010
  10. S. C. Hana, Y. D. Gu, and H. X. Li, "An application of incline matrices in dynamic analysis of generalized fuzzy bidirectional associative memories," Fuzzy Sets and Systems, vol. 158, no. 12, pp. 1340-1347, 2007. https://doi.org/10.1016/j.fss.2007.02.002
  11. O. Qadir, J. Liu, G. Tempesti, J. Timmis, and A. Tyrrell, "From bidirectional associative memory to a noise-tolerant, robust protein processor associative memory," Artificial Intelligence, vol. 175, no. 2, pp. 673-693, 2011. https://doi.org/10.1016/j.artint.2010.10.008
  12. F. Shen, Q. Ouyang, W. Kasai, and O. Hasegawa, "A general associative memory based on self-organizing incremental neural network," Neurocomputing, vol. 104, pp. 57-71, 2013. https://doi.org/10.1016/j.neucom.2012.10.003
  13. M. E. Valle, "Permutation-based finite implicative fuzzy associative memories," Information Sciences, vol. 180, no. 21, pp. 4136-4152, 2010. https://doi.org/10.1016/j.ins.2010.07.003
  14. C. Zhong, W. Pedrycz, Z. Li, D. Wang, and L. Li, "Fuzzy associative memories: a design through fuzzy clustering," Neurocomputing, vol. 173, pp. 1154-1162, 2016. https://doi.org/10.1016/j.neucom.2015.08.072
  15. J. H. Qiang, W. X. Xin, and T. J. Feng, "Improved dynamic subjective logic model with evidence driven," Journal of Information Processing Systems, vol. 11, no. 4, pp. 630-642, 2015. https://doi.org/10.3745/JIPS.03.0030
  16. G. G. Rigatos and S. G. Tzafestas, "Quantum learning for neural associative memories," Fuzzy Sets and Systems, vol. 157, no. 3, pp. 1797-1813, 2006. https://doi.org/10.1016/j.fss.2006.02.012
  17. D. Ventura and T. Martinez, "Quantum associative memory," Information Sciences, vol. 124, no. 1, pp. 273-296, 2000. https://doi.org/10.1016/S0020-0255(99)00101-2
  18. P. Maji and P. P. Chaudhuri, "Non-uniform cellular automata based associative memory: evolutionary design and basins of attraction," Information Sciences, vol. 178, no. 10, pp. 2315-2336, 2008. https://doi.org/10.1016/j.ins.2008.01.004
  19. A. D. Bouchain and G. Palm, "Neural coding in graphs of bidirectional associative memories," Brain Research, vol. 1434, pp. 189-199, 2012. https://doi.org/10.1016/j.brainres.2011.09.050
  20. R. M. Gomes, A. P. Braga, and H. E. Borges, "Information storage and retrieval analysis of hierarchically coupled associative memories," Information Sciences, vol. 195, pp. 175-189, 2012. https://doi.org/10.1016/j.ins.2012.01.036
  21. R. Kalaba, Z. Lichtenstein, T. Simchony, and L. Tesfatsion, "Linear and nonlinear associative memories for parameter estimation," Information Sciences, vol. 61, no. 1-2, pp. 45-66, 1992. https://doi.org/10.1016/0020-0255(92)90033-5
  22. H. Ushida, T. Yamaguchi, K. Goto, and T. Takagi, "Fuzzy-neuro control using associative memories, and its applications," Control Engineering Practice, vol. 2, no. 1, pp. 129-145, 1994. https://doi.org/10.1016/0967-0661(94)90581-9
  23. M. Aldape-Perez, C. Yanez-Marquez, O. Camacho-Nieto, A. J. Arguuelles-Cruz, "An associative memory approach to medical decision support systems," Computer Methods and Programs in Biomedicine, vol. 106, no. 3, pp. 287-307, 2012. https://doi.org/10.1016/j.cmpb.2011.05.002
  24. C. A. Kumar, M. S. Ishwarya, and C. K. Loo, "Formal concept analysis approach to cognitive functionalities of bidirectional associative memory," Biologically Inspired Cognitive Architectures, vol. 12, pp. 20-33, 2015. https://doi.org/10.1016/j.bica.2015.04.003
  25. W. Pedrycz, "The principle of justifiable granularity and an optimization of information granularity allocation as fundamentals of granular computing," Journal of Information Processing Systems, vol. 7, no. 3, pp. 397-412, 2011. https://doi.org/10.3745/JIPS.2011.7.3.397