Discrete Neural Network of Bidirectional Associative Memory

The paper considers bidirectional associative memory, which is one of the known neural network paradigms. To simplify the implementation of the calculation of this paradigm, a discrete mathematical model of its functioning is proposed. Reducing the complexity is achieved by switching to integer calc...

Volledige beschrijving

Bewaard in:

Bibliografische gegevens
Hoofdauteurs:	Shaposhnikov, A. V., Шапошников, А. В., Ionisyan, A. S., Ионисян, А. С., Orazaev, A. R., Оразаев, А. Р.
Formaat:	Статья
Taal:	English
Gepubliceerd in:	2023
Onderwerpen:	Artificial intelligence Neural networks Math modeling Discrete mathematical model Bidirectional associative memory
Online toegang:	https://dspace.ncfu.ru/handle/20.500.12258/25212
Tags:	Voeg label toe Geen labels, Wees de eerste die dit record labelt!

id	ir-20.500.12258-25212
record_format	dspace
spelling	ir-20.500.12258-252122023-09-07T12:15:39Z Discrete Neural Network of Bidirectional Associative Memory Shaposhnikov, A. V. Шапошников, А. В. Ionisyan, A. S. Ионисян, А. С. Orazaev, A. R. Оразаев, А. Р. Artificial intelligence Neural networks Math modeling Discrete mathematical model Bidirectional associative memory The paper considers bidirectional associative memory, which is one of the known neural network paradigms. To simplify the implementation of the calculation of this paradigm, a discrete mathematical model of its functioning is proposed. Reducing the complexity is achieved by switching to integer calculations because Integer multiplication is several times simpler than real multiplication. The known neural network of bidirectional associative memory neural network was compared with the proposed one. The simulation was carried out in the VHDL language. For comparative evaluation, Spartan3E, Spartan6 and XC9500 chips were used. In the experimental part, it was shown that the hardware costs for the implementation of the neural network of bidirectional associative memory have decreased by more than 3 times compared to the known one. The proposed discrete model of BAM functioning does not narrow the scope of its application in comparison with the known model and can be used to build memory devices and restore distorted or noisy information. 2023-09-07T12:14:52Z 2023-09-07T12:14:52Z 2023 Статья Shaposhnikov, A.V., Ionisyan, A.S., Orazaev, A.R. Discrete Neural Network of Bidirectional Associative Memory // Lecture Notes in Networks and Systems. - 2023. - 702 LNNS, pp. 335-342. - DOI: 10.1007/978-3-031-34127-4_32 http://hdl.handle.net/20.500.12258/25212 en Lecture Notes in Networks and Systems application/pdf
institution	СКФУ
collection	Репозиторий
language	English
topic	Artificial intelligence Neural networks Math modeling Discrete mathematical model Bidirectional associative memory
spellingShingle	Artificial intelligence Neural networks Math modeling Discrete mathematical model Bidirectional associative memory Shaposhnikov, A. V. Шапошников, А. В. Ionisyan, A. S. Ионисян, А. С. Orazaev, A. R. Оразаев, А. Р. Discrete Neural Network of Bidirectional Associative Memory
description	The paper considers bidirectional associative memory, which is one of the known neural network paradigms. To simplify the implementation of the calculation of this paradigm, a discrete mathematical model of its functioning is proposed. Reducing the complexity is achieved by switching to integer calculations because Integer multiplication is several times simpler than real multiplication. The known neural network of bidirectional associative memory neural network was compared with the proposed one. The simulation was carried out in the VHDL language. For comparative evaluation, Spartan3E, Spartan6 and XC9500 chips were used. In the experimental part, it was shown that the hardware costs for the implementation of the neural network of bidirectional associative memory have decreased by more than 3 times compared to the known one. The proposed discrete model of BAM functioning does not narrow the scope of its application in comparison with the known model and can be used to build memory devices and restore distorted or noisy information.
format	Статья
author	Shaposhnikov, A. V. Шапошников, А. В. Ionisyan, A. S. Ионисян, А. С. Orazaev, A. R. Оразаев, А. Р.
author_facet	Shaposhnikov, A. V. Шапошников, А. В. Ionisyan, A. S. Ионисян, А. С. Orazaev, A. R. Оразаев, А. Р.
author_sort	Shaposhnikov, A. V.
title	Discrete Neural Network of Bidirectional Associative Memory
title_short	Discrete Neural Network of Bidirectional Associative Memory
title_full	Discrete Neural Network of Bidirectional Associative Memory
title_fullStr	Discrete Neural Network of Bidirectional Associative Memory
title_full_unstemmed	Discrete Neural Network of Bidirectional Associative Memory
title_sort	discrete neural network of bidirectional associative memory
publishDate	2023
url	https://dspace.ncfu.ru/handle/20.500.12258/25212
work_keys_str_mv	AT shaposhnikovav discreteneuralnetworkofbidirectionalassociativememory AT šapošnikovav discreteneuralnetworkofbidirectionalassociativememory AT ionisyanas discreteneuralnetworkofbidirectionalassociativememory AT ionisânas discreteneuralnetworkofbidirectionalassociativememory AT orazaevar discreteneuralnetworkofbidirectionalassociativememory AT orazaevar discreteneuralnetworkofbidirectionalassociativememory
_version_	1809808559900196864

Discrete Neural Network of Bidirectional Associative Memory

Gelijkaardige items