Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)

DOI: http://dx.doi.org/10.15439/2025F6266

Citation: Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 43, pages 133–143 (2025)

Full text

Abstract. This study aims to present a new perspective for creating associative memories using incomplete data and project them into artificial neural networks to retrieve complete data from incomplete data. In previous studies, various approaches to construct associative memories and retrieval of stored data have been proposed. This paper attempts to pin point some of the limitations observed in the existing approaches and propose a way to get rid of that. In particular, a different perspective of comparing two incomplete patterns is proposed and based on that a flexible way of constructing associative patterns of a given input (partial) pattern is developed. Finally, the respective neural network architecture is proposed following similar construction reported in the existing research

References

1. P. M. Churchland, Plato’s camera: How the physical brain captures a landscape of abstract universals. MIT press, 2012. DOI: 10.1080/10848770.2016.1139356. [Online]. Available: https://doi.org/10.7551/mitpress/9116.001.0001.
2. T. M. Mitchell, Machine Learning, 1st ed. USA: McGraw-Hill, Inc., 1997, ISBN : 0070428077. [Online]. Available: https://dl.acm.org/doi/10.5555/541177.
3. C.-H. Chen and V. Honavar, “A neural architecture for content as well as address-based storage and recall: Theory and applications,” Connection Science, vol. 7, no. 3, pp. 281–300, 1995. DOI: 10.1080/09540099509696194.
4. J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities.,” Proceedings of the national academy of sciences, vol. 79, no. 8, pp. 2554–2558, 1982. DOI: 10.1073/pnas.79.8. 2554.
5. B. Prasad, K. Prasad, S. Yeruva, P. Murty, and S. Rama, “A study on associative neural memories,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 1, no. 6, pp. 124–133, 2010. DOI: 10.14569/IJACSA.2010.010619.
6. G. R. Barker and E. C. Warburton, “Multi-level analyses of associative recognition memory: The whole is greater than the sum of its parts,” Current opinion in behavioral sciences, vol. 32, pp. 80–87, 2020. DOI: 10.1016/j.cobeha.2020.02.004.
7. J. Steinberg and H. Sompolinsky, “Associative memory of structured knowledge,” Scientific Reports, vol. 12, no. 1, p. 21 808, 2022. DOI: 10.1038/s41598-022-25708-y.
8. C. H. Chen and V. Honavar, “Neural network architecture for high-speed database query processing,” Microcomputer Applications, vol. 15, no. 1, pp. 7–13, 1996, ISSN: 0820-0750. [Online]. Available: https://dr.lib.iastate.edu/handle/20.500.12876/20228.
9. C. F. Caiafa, Z. Wang, J. Solé-Casals, and Q. Zhao, “Learning from incomplete data by simultaneous training of neural networks and sparse coding,” arXiv preprint https://arxiv.org/abs/2011.14047, 2020. DOI : 10.48550/arXiv.2011.14047.
10. W.-D. Chang, J. Shin, M.-Y. Song, and T.-S. Chon, “Enhanced back propagation algorithm for estimating ecological data with missing values,” WSEAS Transactions on Computers, vol. 5, no. 9, pp. 2043–2048, Sep. 2006.
11. C. Chen and V. Honavar, “Neural network automata,” in Proc. of World Congress on Neural Networks, vol. 4, 1994, pp. 470–477.
12. P. Watta and M. H. Hassoun, “Generalizations of the hamming associative memory,” Neural processing letters, vol. 13, no. 2, pp. 183–194, 2001. DOI: 10.1023/A:1011384407294.
13. T. Park, I. Choi, and M. Lee, “Distributed associative memory network with memory refreshing loss,” Neural Networks, vol. 144, pp. 33–48, 2021. DOI: 10.1016/j.neunet.2021.07.030.