Abstract—
The organization of associative memory plays a crucial role in the efficiency of intelligent systems, software, and practical applications that require analysis and processing of big data and knowledge. A logical architecture of a neuro-like hierarchical pattern associative memory system, which provides storage of incoming information in the form of so-called patterns, is proposed and described. Patterns are hierarchically organized memory elements that make it possible to recover data from its part and find elements within automatically determined contexts on the basis of previously stored information. Modern approaches to the organization of associative memory in intelligent systems are considered. The main elements of pattern memory, i.e., pattern, neuron, mediator, and synapse, are defined. The basic concepts and principles of functioning of hierarchical pattern associative memory systems are described, and examples of practical implementation are given. Based on the principles described, it is possible to create specific memory versions for practical tasks, such as processing text, graphic, audio, and video information. Shared memory can be used to generalize various information flows into common logical chains of memories. It is concluded that the capabilities of the proposed hierarchical pattern memory systems for handling data make it possible to store information in intelligent systems and model the thinking process of an expert in the course of logical reasoning.
Similar content being viewed by others
REFERENCES
Meijia, S. and Xiaoping, W., A memristor-based circuit design for generalization and differentiation on Pavlov associative memory, Neurocomputing, 2020, vol. 389, pp. 18–26. https://doi.org/10.1016/j.neucom.2019.12.106
Jalaleddine, S.M., Associative memories and processors: The exact match paradigm, J. King Saud Univ. - Comput. Inf. Sci., 1999, vol. 11, pp. 45–67. https://doi.org/10.1016/S1319-1578(99)80003-2
Tiba, A.K.O. and Araujo, A.F.R., Control strategies for Hopf bifurcation in a chaotic associative memory, Neurocomputing, 2019, vol. 323, pp. 157–174. https://doi.org/10.1016/j.neucom.2018.09.078
Li, L., Pedrycz, W., Qu, T., and Li, Z., Fuzzy associative memories with autoencoding mechanisms, Knowl.-Based Syst., 2020, vol. 191, p. 105090. https://doi.org/10.1016/j.knosys.2019.105090
Ramírez-Rubio, R., Aldape-Pérez, M., Yáñez-Márquez, C., López-Yáñez, I., and Camacho-Nieto, O., Pattern classification using smallest normalized difference associative memory, Pattern Recognit. Lett., 2017, vol. 93, pp. 104–112. https://doi.org/10.1016/j.patrec.2017.02.013
Kobayashi, M., Chaotic pseudo-orthogonalized Hopfield associative memory, Neurocomputing, 2017, vol. 241, pp. 147–151. https://doi.org/10.1016/j.neucom.2017.02.037
Miyata, M. and Omori, T., Emergence of symbolic inference based on value-driven intuitive inference via associative memory, Procedia Comput. Sci., 2018, vol. 145, pp. 370–375. https://doi.org/10.1016/j.procs.2018.11.087
Masuyama, N., Loo, C.K., and Seera, M., Personality affected robotic emotional model with associative memory for human-robot interaction, Neurocomputing, 2018, vol. 272, pp. 213–225. https://doi.org/10.1016/j.neucom.2017.06.069
Sussner, P. and Schuster, T., Interval-valued fuzzy morphological associative memories: some theoretical aspects and applications, Inf. Sci., 2018, vol. 438, pp. 127–144. https://doi.org/10.1016/j.ins.2018.01.042
Pedrycz, A., Bidirectional and multidirectional associative memories as models in linkage analysis in data analytics: conceptual and algorithmic developments, Knowl.-Based Syst., 2018, vol. 142, pp. 160–169. https://doi.org/10.1016/j.knosys.2017.11.034
De Paula Neto, F.M., da Silva, A.J., de Oliveira, W.R., and Ludermir, T.B., Quantum probabilistic associative memory architecture, Neurocomputing, 2019, vol. 351, pp. 101–110. https://doi.org/10.1016/j.neucom.2019.03.078
Majdabadi, M.M., Shokouhi, S.B., and Ko, S.-B., Efficient hybrid cmos/memristor implementation of bidirectional associative memory using passive weight array, Microelectron. J., 2020, vol. 98, p. 104725. https://doi.org/10.1016/j.mejo.2020.104725
Wang L. and Zou H., A new emotion model of associative memory neural network based on memristor, Neurocomputing, 2020, vol. 410, pp. 83–92. https://doi.org/10.1016/j.neucom.2020.05.002
Zhdanov, A.A., Avtonomnyi iskusstvennyi intellekt (Autonomous Artificial Intelligence), Moscow: Laboratoriya Znanii, 2015.
Zueva, E.Yu. and Efimov, G.B., Principle of dominance of Ukhtomsky as approach to describing life, Preprint of Keldysh Inst. for Appl. Math., Moscow, 2010, no. 16.
Savel’ev, A.V., Ontological extension of the theory of functional systems, Zh. Probl. Evol. Otrkrytykh Sist., 2005, no. 1, p. 7.
Kulmagambetov, I.R., Koichubekov, B.K., and Riklefs, V.P., Basic concepts of the theory of deterministic chaos and its applied aspects in physiology, Med. Ekol., 2007, no. 1, p. 42. https://cyberleninka.ru/article/n/osnovnye-polozheniya-teorii-determinirovannogo-haosa-i-ee-prikladnye-aspekty-v-fiziologii.
ACKNOWLEDGMENTS
We thank S.P. Smirnov, Candidate of Engineering Sciences, for scientific ideas and participation in discussions during the research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The author declare that they have no conflicts of interest.
Additional information
Translated by O. Pismenov
About this article
Cite this article
Stepanyan, I.V. Neural Network Modeling and Organization of a Hierarchical Associative Memory System. J. Mach. Manuf. Reliab. 50, 735–742 (2021). https://doi.org/10.3103/S1052618821080148
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1052618821080148