THE CONCEPT OF USING THE NUMBER SYSTEM IN THE RESIDUAL CLASSES FOR BUILDING ARTIFICIAL INTELLIGENCE SYSTEM
DOI:
https://doi.org/10.26906/SUNZ.2022.1.065Keywords:
artificial intelligence, number system in residual classes, information processing by the human brain, nonpositional number systemAbstract
The subject of the article is the consideration of the concept of constructing an artificial intelligence (AI) system based on the use of a non-positional system of residual classes (RNS). This concept is based on the hypothesis of the holographic principle of building the memory of biological systems. The purpose of the article is to consider a method for constructing an information model of the process of information processing by the human brain, based on the ass umption that the storage and processing of information is carried out in the RNS. Tasks: to consider a model of the process of information processing by the human brain; consider the proposed model of information processing by the human brain in the RNS; to study the influence of RNS properties in the creation of intelligent computing systems. Research methods:methods of analysis and synthesis of computer systems, data analysis, number theory, coding theory in RNS. The following results are obtained. The article considers a model of the process of information processing by the human brain, based on the assumption that the storage and processing of information is carried out in the RNS. When accepting the hypothesis of the holographic principle of information processing by the human brain, the expediency and efficiency of building AI systems based on the information processing model in RNS is obvious. This is due to the fact that the principles and methods of information processing in the RNS are in good agreement with modern ideas about the process of information processing by the human brain. The accuracy of the description (representation) of the information object G depends on the number and value of RNS bases. So, the greater the number of RNS bases and the greater their value, the more accurately the information object G is described using frames. This fact confirms the feasibility of using RNS. Conclusions. The main idea of the study is to consider the hypothesis of the holographic principle of building the memory of biological systems. In this case, the failure of one or more memory cells does not affect the normal functioning of the biological model of the brain, i.e. each unit of initial information is distributed over the entire surface of the hologram. In the article, AI is presented as a model of computational processes operating in RNS. Thus, the expediency and efficiency of building AI systems based on the information processing model functioning in the RNS is assessed as obvious.Downloads
References
A. Kaplan and M. Haenlein, "Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence," Business Horizons, vol. 62, no. 1, pp. 15–25, Jan. 2019, doi: 10.1016/j.bushor.2018.08.004.
S. E. Dreyfus, "Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedure," Journal of Guidance, Control, and Dynamics, vol. 13, no. 5, pp. 926–928, Sep. 1990, doi: 10.2514/3.25422.
J. Schmidhuber, "Deep learning in neural networks: An overview," Neural Networks, vol. 61, pp. 85–117, Jan. 2015, doi: 10.1016/j.neunet.2014.09.003.
P. A. Vikhar, "Evolutionary algorithms: A critical review and its future prospects," in 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC), Dec. 2016, pp. 261–265. doi: 10.1109/ICGTSPICC.2016.7955308.
L. A. Zadeh, "Fuzzy sets," Information and Control, vol. 8, no. 3, pp. 338–353, Jun. 1965, doi: 10.1016/S0019-9958(65)90241-X.
F. J. Pelletier, "Petr Hájek. Metamathematics of fuzzy logic. Trends in logic, vol. 4. Kluwer Academic Publishers, Dordrecht, Boston, and London, 1998, viii + 297 pp.," Bulletin of Symbolic Logic, vol. 6, no. 3, pp. 342–346, Sep. 2000, doi: 10.2307/421060.
V.M. Amerbaev, R.A. Solovyev, A.L. Stempkovskiy, D.V. Telpukhov, "Efficient calculation of cyclic convolution by means of fast Fourier transform in a finite field", in: Proceedings of IEEE East-West Design Test Symposium (EWDTS 2014), 2014:pp. 1–4. https://doi.org/10.1109/EWDTS.2014.7027043.
"White Paper on Artificial Intelligence: a European approach to excellence and trust," European Commission - European Commission. https://ec.europa.eu/info/publications/white-paper-artificial-intelligence-european-approach-excellence-and-trust_en (accessed Apr. 23, 2021).
A. S. Tanenbaum and M. V. Steen, Distributed Systems: Principles and Paradigms, US Ed edition. Upper Saddle River, N.J: Prentice Hall, 2002.
A. Lieto, C. Lebiere, and A. Oltramari, "The knowledge level in cognitive architectures: Current limitations and possible developments," Cognitive Systems Research, vol. 48, pp. 39–55, May 2018, doi: 10.1016/j.cogsys.2017.05.001.
J. O. Tuazon, "Residue number system in computer arithmetic," Doctor of Philosophy, Iowa State University, Digital Repository, Ames, 1969. doi: 10.31274/rtd-180816-2270.
J. L. P. velazquez and R. Wennberg, Eds., Coordinated Activity in the Brain, Measurements and Relevance to Brain Function and Behavior. New York: Springer-Verlag, 2009. doi: 10.1007/978-0-387-93797-7.
O. Goloubeva, M. Rebaudengo, M. S. Reorda, and M. Violante, Eds., "Achieving Fault Tolerance," in Software-Implemented Hardware Fault Tolerance, Boston, MA: Springer US, 2006, pp. 117–151. doi: 10.1007/0-387-32937-4_4.
V. Krasnobayev, A. Kuznetsov, A. Yanko, and T. Kuznetsova, "The analysis of the methods of data diagnostic in a residue number system," in Proceedings of The Third International Workshop on Computer Modeling and Intelligent Systems (CMIS-2020), Zaporizhzhia, Ukraine, April 27-May 1, 2020, 2020, vol. 2608, pp. 594–609. Accessed: Jul. 02, 2020. [Online]. Available: http://ceur-ws.org/Vol-2608/paper46.pdf
Y. Zhang, "An FPGA implementation of redundant residue number system for low-cost fast speed fault-tolerant computations," Thesis, 2018. doi: 10.32657/10220/47113.
V. Krasnobayev, A. Kuznetsov, A. Yanko, and K. Kuznetsova, "The data errors control in the modular number system based on the nullification procedure," in Proceedings of The Third International Workshop on Computer Modeling and Intelligent Systems (CMIS-2020), Zaporizhzhia, Ukraine, April 27-May 1, 2020, 2020, vol. 2608, pp. 580–593. Accessed: Jul. 02, 2020. [Online]. Available: http://ceur-ws.org/Vol-2608/paper45.pdf
D.I. Popov, A.V. Gapochkin, "Development of Algorithm for Control and Correction of Errors of Digital Signals, Represented in System of Residual Classes", in: 2018 International Russian Automation Conference (RusAutoCon), 2018: pp. 1–3. https://doi.org/10.1109/RUSAUTOCON.2018.8501826.
P.V. Ananda Mohan, "Specialized Residue Number Systems", in: P.V.A. Mohan (Ed.), Residue Number Systems: Theory and Applications, Springer International Publishing, Cham, 2016: pp. 177–193. https://doi.org/10.1007/978-3-319-41385-3_8.
D. I. Popov and A. V. Gapochkin, "Development of Algorithm for Control and Correction of Errors of Digital Signals, Represented in System of Residual Classes," in 2018 International Russian Automation Conference (RusAutoCon), Sep. 2018, pp. 1–3. doi: 10.1109/RUSAUTOCON.2018.8501826.
T.-C. Huang, "Self-Checking Residue Number System for Low-Power Reliable Neural Network," in 2019 IEEE 28th Asian Test Symposium (ATS), Dec. 2019, pp. 37–375. doi: 10.1109/ATS47505.2019.000-3.
