Article 1420

Title of the article

A COMPACT GRAPHIC AND HIEROGLYPHIC SYSTEM FOR DISPLAYING SCHEMES OF DIVERSE NEURAL NETWORK CALCULATIONS 

Authors

Ivanov Aleksandr Ivanovich, Doctor of engineering sciences, associate professor, consultant, Penza Research Institute of Electrical Engineering (9 Sovetskaya street, Penza, Russia), bio.ivan.penza@mail.ru
Malygina Elena Aleksandrovna, Candidate of engineering sciences, doctor’s degree student of the subdepartment of information security technology, Penza State University (40 Krasnaya street, Penza, Russia), mal890@yandex.ru 
Lukin Vitaliy Sergeevich, Junior researcher, Regional Training and Research Center of «Information security», Penza State University (40 Krasnaya street, Penza, Russia),ibst@pnzgu.ru

Index UDK

004.056; 004.032.26 

DOI

10.21685/2072-3059-2020-4-1 

Abstract

Background. The purpose of this article is to try to eliminate ambiguities in the verbal description and graphic representations of schemes of multi-dimensional neural network calculations while reducing the volume of text and graphic information.
Materials and methods. By the analogy with the standard description of Boolean logic, it is purposed to introduce a finite number of designations for the types of artificial neurons. It is also proposed to use elements of hieroglyphic image formation when graphically displaying artificial neurons (smooth ovals are continual transformations, and angular rectangles are operations for quantizing continuous data). When artificial neurons with multilevel quantization are used, their rectangular quantizers get several outputs.
Results. The proposed standardization version of the alphabet of graphic symbols leads to an ambiguity’s decrease in the graphic illustrations of schemes for diverse neural network calculations and an increase in the compactness of the created illustrative materials.
Conclusions. The proposed scheme for the formation of graphic and hieroglyphic illustrations is compact (does not lead to the appearance of thousands of hieroglyphs) and allows using a small number of basic images to visually illustrate the vast majority of neural network calculation schemes known to the authors. 

Key words

classification of artificial neurons, graphic representation of neurons, elements of hieroglyphic records 

Download PDF
References

1. Khaykin S. Neyronnye seti: polnyy kurs [Neural networks: complete course]. Moscow: Vil'yams, 2006, p. 1104. [In Russian]
2. Rassel S., Norvig P. Iskusstvennyy intellekt. Sovremennyy podkhod [Artificial Intelligence. Modern approach]. Moscow; Saint-Petersburg; Kiev, 2006, 1407 p. [In Russian]
3. Nikolenko S., Kadurin A., Arkhangel'skaya E. Glubokoe obuchenie [In-depth study]. Saint-Petersburg: Piterb, 2018, 480 p. [In Russian]
4. GOST R 52633.0–2006. Zashchita informatsii. Tekhnika zashchity informatsii. Trebovaniya k sredstvam vysokonadezhnoy biometricheskoy autentifikatsii [Data protection. Information security technology. Requirements for highly secure biometric authentication tools]. Moscow, 2006. [In Russian]
5. GOST R 52633.1–2009. Zashchita informatsii. Tekhnika zashchity informatsii. Trebovaniya k formirovaniyu baz estestvennykh biometricheskikh obrazov, prednaznachennykh dlya testirovaniya sredstv vysokonadezhnoy biometricheskoy autentifikatsii [Data protection. Information security technology. Requirements for the formation of databases of natural biometric images intended for testing highly reliable biometric authentication facilities]. Moscow, 2009. [In Russian]
6. GOST R 52633.2–2010. Zashchita informatsii. Tekhnika zashchity informatsii. Trebovaniya k formirovaniyu sinteticheskikh biometricheskikh obrazov, prednaznachennykh dlya testirovaniya sredstv vysokonadezhnoy biometricheskoy autentifikatsii [Data protection. Information security technology. Requirements for the formation of synthetic biometric images intended for testing a highly reliable biometric authentication facility]. Moscow, 2010. [In Russian]
7. GOST R 52633.3–2011. Zashchita informatsii. Tekhnika zashchity informatsii. Testirovanie stoykosti sredstv vysokonadezhnoy biometricheskoy zashchity k atakam podbora [Data protection. Information security technology. Testing the resistance of highly reliable biometric security to brute force attacks]. Moscow, 2011.
8. GOST R 52633.5–2011. Zashchita informatsii. Tekhnika zashchity informatsii. Avtomaticheskoe obuchenie neyrosetevykh preobrazovateley biometriya-kod dostupa [Data protection. Information security technology. Automatic training of neural network converters biometrics-access code]. Moscow, 2011. [In Russian]
9. Zashchita neyrosetevykh biometricheskikh konteynerov s ispol'zovaniem kriptograficheskikh algoritmov» [proekt tekhnicheskoy spetsifikatsii «Kriptograficheskaya zashchita informatsii] Publichnoe obsuzhdenie dokumenta prokhodit v TK 26 s 2017 g., v 2020 g. ozhidaetsya golosovanie po proektu tekhnicheskoy spetsifikatsii [Protection of neural network biometric containers using cryptographic algorithms [draft technical specification “Cryptographic protection of information”]. Public discussion of the document has been taking place in TC 26 since 2017; a vote on the draft technical specification is expected in 2020]. [In Russian]
10. Volchikhin V. I., Ivanov A. I., Akhmetov B. B., Serikova Yu. I. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki [University proceedings. Volga region. Engineering sciences]. 2016, no. 4, pp. 25–31. [In Russian]
11. Volchikhin V. I., Ivanov A. I., Malygina E. A., Serikova Yu. I. Izmerenie. Monitoring. Upravlenie. Kontrol' [Measurement. Monitoring. Operation. Control]. 2018, no. 1 (23), pp. 66–74. [In Russian]
12. Ivanov A. I., Kupriyanov E. N. Zashchita iskusstvennogo intellekta: ortogonalizatsiya statistiko-neyrosetevogo analiza malykh vyborok biometricheskikh dannykh: preprint [Artificial intelligence protection: orthogonalization of statistic neural network analysis of small samples of biometric data: preprint]. Penza: Izd-vo PGU, 2020, 72 p. [In Russian]
13. Ivanov A. I. Iskusstvennye matematicheskie molekuly: povyshenie tochnosti statisticheskikh otsenok na malykh vyborkakh (programmy na yazyke MathCAD): prepreprint [Artificial mathematical molecules: improving the accuracy of statistical estimates on small samples (programs in the MathCAD language): preprint]. Penza: Izd-vo PGU, 2020, 36 p. [In Russian]
14. Malygina E. A. Biometriko-neyrosetevaya autentifikatsiya: perspektivy primeneniya setey kvadratichnykh neyronov s mnogourovnevym kvantovaniem biometricheskikh dannykh: preprint [Biometrical-neural network authentication - prospects for the use of networks of square neurons with multilevel quantization of biometric data: preprint]. Penza: Izd-vo PGU, 2020, 114 p. [In Russian]
15. Volchikhin V. I., Ivanov A. I., Funtikov V. A., Malygina E. A. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki [University proceedings. Volga region. Engineering sciences]. 2013, no. 4 (28), pp. 88–99. [In Russian]
16. Volchikhin V. I., Ivanov A. I., Malygina E. A., Yunin A. P. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki [University proceedings.
Volga region. Engineering sciences]. 2018, no. 1 (45), pp. 17–25. [In Russian]
17. Volchikhin V. I., Ivanov A. I., Malygina E. A., Serikova Yu. I. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki [University proceedings. Volga region. Engineering sciences]. 2018, no. 3 (47), pp. 47–57. [In Russian]
18. Volchikhin V. I., Ivanov A. I., Vyatchanin S. E. Novye informatsionnye tekhnologii i sistemy: sb. nauch. st. XIV Mezhdunar. nauch.-tekhn. konf. (g. Penza, 22–24 noyabrya 2017 g.) [New information technologies and systems: proceedings of the 14th International scientific and engineering conference (Penza, 22-24 of November 2017)]. Penza: Izd-vo PGU, 2017, pp. 159–163. [In Russian]
19. Volchikhin V. I., Ivanov A. I., Vyatchanin S. E., Malygina E. A. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki [University proceedings. Volga region. Engineering sciences]. 2017, no. 2 (42), pp. 55–65. [In Russian]
20. Ivanov A. I., Bezyaev A. V., Malygina E. A., Serikova Yu. I. Bezopasnost' informatsionnykh tekhnologiy: sb. nauch. st. po materialam I Vseross. nauch.-tekhn. konf.
(g. Penza, 24 aprelya 2019 g.) [Information technology security: proceedings of the 1st All-Russian scientific and engineering conference (Penza, April 24, 2019)]. Penza: Izdvo PGU, 2019, pp. 174–177. [In Russian]
21. Standart TK 362. Zashchita informatsii. TEKhNIKA ZAShchITY INFORMATsII. Avtomaticheskoe obuchenie setey kvadratichnykh neyronov s mnogourovnevym kvantovaniem biometricheskikh dannykh [proekt]. Raboty nachaty s 01.07.2018 i velis' spetsialistami 5 predpriyatiy (Voronezh, Penza, Moskva). 01.02.2019 materialy napravleny v TK 362. V nastoyashchee vremya vedetsya podgotovka k nachalu publichnogo obsuzhdeniya proekta novogo standarta [TC 362 standard. Information protection. Information security technology. Automatic training of networks of quadratic neurons with multilevel quantization of biometric data (project). The work began on July 1, 2018 and was carried out by specialists from five enterprises (Voronezh, Penza and Moscow). On February 1, 2019, materials were sent to TC 362. Currently, preparations are underway for the start of a public discussion of the draft new standard]. [In Russian]
22. Volchikhin V. I., Ivanov A. I. Vestnik Mordovskogo universiteta [Bulletin of Mordovia University]. 2017, vol. 27, no. 4, pp. 518–523. [In Russian]
23. Yazov Yu. K., Volchikhin V. I., Ivanov A. I., Funtikov V. A., Nazarov I. G. Neyrosetevaya zashchita personal'nykh biometricheskikh dannykh [Neural network protection of personal biometric data]. Moscow: Radiotekhnika, 2012, 157 p. [In Russian]

 

Дата создания: 17.02.2021 12:08
Дата обновления: 17.02.2021 12:49