Multirecurrent Neural Network in Discrete Form

The paper considers paradigms for constructing a multirecurrent neural network (MRNN) of Jordan and Elman. The use of these paradigms is limited by the complexity of data processing due to real arithmetic. To simplify the implementation of neurocomputations of the considered MRNN, it is proposed to...

Полное описание

Сохранить в:

Библиографические подробности
Главные авторы:	Shaposhnikov, A. V., Шапошников, А. В., Ionisyan, A. S., Ионисян, А. С., Orazaev, A. R., Оразаев, А. Р.
Формат:	Статья
Язык:	English
Опубликовано:	Springer Science and Business Media Deutschland GmbH 2024
Темы:	Artificial intelligence Math modeling Data processing Integer arithmetic Neural networks
Online-ссылка:	https://dspace.ncfu.ru/handle/123456789/29205
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!

id	ir-123456789-29205
record_format	dspace
spelling	ir-123456789-292052024-11-05T11:13:26Z Multirecurrent Neural Network in Discrete Form Shaposhnikov, A. V. Шапошников, А. В. Ionisyan, A. S. Ионисян, А. С. Orazaev, A. R. Оразаев, А. Р. Artificial intelligence Math modeling Data processing Integer arithmetic Neural networks The paper considers paradigms for constructing a multirecurrent neural network (MRNN) of Jordan and Elman. The use of these paradigms is limited by the complexity of data processing due to real arithmetic. To simplify the implementation of neurocomputations of the considered MRNN, it is proposed to use integer arithmetic. To solve the problem, an analysis of the continuous model of the MRNN functioning was carried out, instead of which a discrete mathematical model was proposed. The advantage of using a discrete MRNN over the known one, in addition to using integer arithmetic, is also the possibility of obtaining the topology of a neural network based on the conditions of the problem being solved. In the MRNN, the structure of the neural network is formed through a complex neural network training procedure. To confirm the correct functioning of the discrete MRNN, a computer model has been developed. Analysis of the functioning of the developed computer model on the example of time series analysis indicates the correctness of the proposed discrete model of MRNN. To compare the hardware implementation of the discrete and MRNN, their models were compiled based on the simulation of firmware for FPGA microcircuits in the VHDL language. Based on the simulation, it can be concluded that the use of a discrete network can increase performance by 17% and reduce hardware costs by 3.7 times compared to the known MRNN. 2024-11-05T11:09:48Z 2024-11-05T11:09:48Z 2024 Статья Shaposhnikov A.V., Ionisyan A.S., Orazaev A.R. Multirecurrent Neural Network in Discrete Form // Lecture Notes in Networks and Systems. - 2024. - 1044 LNNS. - pp. 389 - 397. - DOI: 10.1007/978-3-031-64010-0_36 https://dspace.ncfu.ru/handle/123456789/29205 en Lecture Notes in Networks and Systems application/pdf Springer Science and Business Media Deutschland GmbH
institution	СКФУ
collection	Репозиторий
language	English
topic	Artificial intelligence Math modeling Data processing Integer arithmetic Neural networks
spellingShingle	Artificial intelligence Math modeling Data processing Integer arithmetic Neural networks Shaposhnikov, A. V. Шапошников, А. В. Ionisyan, A. S. Ионисян, А. С. Orazaev, A. R. Оразаев, А. Р. Multirecurrent Neural Network in Discrete Form
description	The paper considers paradigms for constructing a multirecurrent neural network (MRNN) of Jordan and Elman. The use of these paradigms is limited by the complexity of data processing due to real arithmetic. To simplify the implementation of neurocomputations of the considered MRNN, it is proposed to use integer arithmetic. To solve the problem, an analysis of the continuous model of the MRNN functioning was carried out, instead of which a discrete mathematical model was proposed. The advantage of using a discrete MRNN over the known one, in addition to using integer arithmetic, is also the possibility of obtaining the topology of a neural network based on the conditions of the problem being solved. In the MRNN, the structure of the neural network is formed through a complex neural network training procedure. To confirm the correct functioning of the discrete MRNN, a computer model has been developed. Analysis of the functioning of the developed computer model on the example of time series analysis indicates the correctness of the proposed discrete model of MRNN. To compare the hardware implementation of the discrete and MRNN, their models were compiled based on the simulation of firmware for FPGA microcircuits in the VHDL language. Based on the simulation, it can be concluded that the use of a discrete network can increase performance by 17% and reduce hardware costs by 3.7 times compared to the known MRNN.
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	Multirecurrent Neural Network in Discrete Form
title_short	Multirecurrent Neural Network in Discrete Form
title_full	Multirecurrent Neural Network in Discrete Form
title_fullStr	Multirecurrent Neural Network in Discrete Form
title_full_unstemmed	Multirecurrent Neural Network in Discrete Form
title_sort	multirecurrent neural network in discrete form
publisher	Springer Science and Business Media Deutschland GmbH
publishDate	2024
url	https://dspace.ncfu.ru/handle/123456789/29205
work_keys_str_mv	AT shaposhnikovav multirecurrentneuralnetworkindiscreteform AT šapošnikovav multirecurrentneuralnetworkindiscreteform AT ionisyanas multirecurrentneuralnetworkindiscreteform AT ionisânas multirecurrentneuralnetworkindiscreteform AT orazaevar multirecurrentneuralnetworkindiscreteform AT orazaevar multirecurrentneuralnetworkindiscreteform
_version_	1842245574803324928

Multirecurrent Neural Network in Discrete Form

Схожие документы