REALIZATION MODEL OF ADAPTIVE SUMMATOR FOR NEURAL-LIKE ELEMENTS
DOI:
https://doi.org/10.31649/1999-9941-2020-49-3-45-53Keywords:
adaptive adder, multioperand summation, neural-like elements, neurotechnologiesAbstract
One of the promising areas for the use of neurotechnologies is robotics, namely, systems of technical vision and control systems for mobile robots of various applications. In particular, one of the basic tasks for these systems as part of autonomous robots is the task of object recognizing and determining of the obstacles contours in the movement of mobile robots in a non-deterministic environment. For a compact and reliable implementation of the basic units of these systems, there is no alternative) the use of neural network technologies with to focusing on perspective modern tools (FPGA). It is necessary to take into account the simultaneous perception of visual information, which requires, in turn, parallel spatially distributed processing of large amounts of information. The work proposes the structure of the adaptive adder in composition of artificial neurons, which are basic neural-like elements of different types of neural networks. The proposed pipeline summing device has advanced functionality, as it simulates the operation of the adaptive adder in the formal neuron with the formation of the result of processing taking into account the external bias with the sign, and also performs parallel summation of vector array numbers with the formation of their sum. The proposed adaptive adder has a regular structure consisting of (n+1) cells with almost the same set of units and connections between them, and also implements a spatially distributed process of parallel processing over n input elements of the vector array. All this simplifies the process of placing the adaptive adder in the FPGA chip. The orientation on functionally and technologically powerful FPGA chips allows to get compact and full-featured neurostructures for various purposes, the need for which is extremely important in the control systems of mobile robots.
References
M. T. Dzhons, Programmirovanie iskusstvennogo intellekta, per. s angl. M.: Rossiya: DMK Press, 2004.
P. I. Kravets, V. M. Shimkovich, O. I. Nikolin, «Neyromerezheva sistema mashinnogo bachennya z aparatno-programnoyu realizatsieyu na PLIS», Naukoviy zhurnal «Molodiy vcheniy», № 5 (20), s. 47‒50. 2015.
A. V. Gavrilov, V. V. Gubarev, K. H. Dzho, H. H. Li, «Arhitektura gibridnoy intellektualnoy sistemyi upravleniya mobilnogo robota», Vestnik NTTU, № 2, s. 3‒13. 2004.
A. I. Korendyasev, B. L. Salamandra, L. I. Tyives, Teoreticheskie osnovyi robototehniki. M., Rossiya: Nauka, 2006.
T. B. Martyniuk, A. V. Kozhemiako, N. O. Denisyuk, T. Yu. Pozdnyakova, «Analіz operatsіynogo bazisu dlya neyromerezhevih Intelektualnih sistem», Informatsіynі tehnologyi ta komyuterna inzhenerіya, № 2 (33), s. 83‒87. 2015.
T. B. Martyniuk, A. V. Kozhemiako, L. M. Kupershteyn, O. S. Bezkrevniy, «Operatsіyno-elementniy bazis dlya іntelektualnih sistem», Vіsnik Hmelnitskogo natsіonalnogo unіversitetu, № 6, s. 37‒44. 2019.
S. A. Vasiletskiy, O. K. Kolesnitskiy, «Matematichne ta kompyuterne modelyuvannya optoelektronnogo chastotno-dinamichnogo neyronnogo elementa», Optiko-elektronnі Informatsіyno-energetichnі tehnologyi, № 2, s. 96‒101. 2001.
Neural Network-Systems Techniques and Applications, Algorithms and Architectures, Edited by Cornelius T. Leondes, Academic Press, 465 pp. 1998.
T. B. Martyniuk, V. V. Homyuk, «Osobennosti matematicheskoy modeli diskretnogo SM-preobrazovaniya», Matematichni mashini i sistemi, № 4, s.145‒155. 2010.
L. Timchenko, M. Grudin, T. Martyniuk, A. Kozhemiako, «Parallel Transformation», Upravlyayuschie sistemi i mashiny, № 5, s. 93‒95. 1998.
T. B. Martyniuk, L. Kupershteyn, A. Kozhemiako, Aspekty raznostno-srezovoy obrabotki dannyih v neyrostrukturah. LAMBERT Academic Publishing, 2018.
A. S. Vasyura, T. B. Martyniuk, L. M. Kupershteyn Metodi ta zasobi neyropodibnoi obrobki danih dlya sistem keruvannya. VInnitsya, UkraYina: UNIVERSUM–VInnitsya, 2008.
T. B. Martyniuk, «Model porogovogo neyrona na osnove parallelnoy obrabotki po raznostnyim srezam», Kibernetika i sistemnyi analiz, № 4, s. 78‒89. 2005.
V. P. Kozhemiako, T. B. Martyniuk, L. M. Kupershteyn, «Model “byistrogo neyrona” s obrabotkoy dannyih po printsipu raznostnyih srezov», Optiko-elektronns Informatsiyno-energetichni tehnologiyi, № 2 (18), s. 87‒98. 2009.
T. Martyniuk, A. Kozhemiako, A. Buda, L. Kupershtein, «The model of multifunctional neural element of intelligent systems», Education-Technology-Computer science, Main problems of informatics and information education: Scientific annual №/4/2013/part 2. Rzeszow, Poland: pp. 366‒371. 2013.
T. B. Martyniuk, L. I. Timchenko, L. M. Kupershteyn, «Apparatnaya realizatsiya modeli formalnogo neyrona», Elektronnoe modelirovanie, T. 32, № 4, s. 35‒47. 2010.
T. B. Martyniuk, A. V. Kozhemiako, V. V. Homyuk, «Modeli sistolicheskih massivov dlya obrabotki vektornyih dannyih po raznostnyim srezam», Upravlyayuschie sistemyi i mashiny, № 5, s. 46–55. 2009.
T. B. Martyniuk, A. V. Kozhemiako, N. V. Fofanova, O.M. Nakonechniy, «Adaptivniy sumator dlya sistemi keruvannya robotom», Optiko-elektronni Informatsiyno-energetichni tehnologiyi, № 2 (10), s. 96‒101. 2005.
T. B. Martyniuk, L. I. Timchenko, A. V. Kozhemiako, L. M. Kupershteyn, «Effektivnost posrezovoy obrabotki vektornyih massivov dannyih», Matematichni mashini i sistemi, № 2, s. 60-67. 2017.
T. B. Martyniuk, V. V. Homyuk, «Multiobrabotka massivov dannyih po raznostnyim srezam», Kibernetika i sistemnyiy analiz, № 6, s. 132‒137. 2011.
V. V. Kruglov, V. V. Borisov, Iskusstvennyie neyronnyie seti. Teoriya i praktika, 2-e izd. M., Rossiya: Goryachaya liniya – Telekom, 2002.
T. B. Martyniuk, A. V. Kozhemiako, L. M. Kupershteyn I A. V. Shepotailo, «Konveerniy pidsumovuyuchiy pristriy», Patent Ukraini G06G7/14. №142771 U,
T. B. Martinyuk, A. V. Kozhemiako, Sistolschni strukturi dlya bagatooperandnoi obrobki vektornih danih. Vinnitsya, Ukraina: UNIVERSUM-Vinnitsya, 2007.
V. V. Korablev, V. A. Korablev, «Ispolzovanie iskusstvennogo intellekta v prikladnoy robototehnike», na 2-y Mizhnar. nauk.-tehn. konf. Obchislyuvalniy Intelekt (rezultati, problemi, perspektivi) «OI-2015», Cherkasi, 2015, s. 213‒214.
V. Ababiy, V Sudachevskiy, M. Podubnyiy, G. Safonov «Sistema mobilnyih robotov dlya poiska istochnikov yoniziruyuschey radiatsiy», na 2-y Mizhnar. nauk.-tehn. konf. Obchislyuvalniy Intelekt (rezultati, problemi, perspektivi) «OI-2015», Cherkasi, 2015, s. 163‒164.
Downloads
-
PDF (Українська)
Downloads: 164
