Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks

In this paper, the presented method, applied to transpose densified weight matrices, involves tenth machine learning when moving from feedforward to backpropagation. The algorithm is based on the diagonal matrix construction method. The process of manufacturing change will significantly increase the...

Полное описание

Сохранить в:

Библиографические подробности
Главные авторы:	Bezuglova, E. S., Безуглова, Е. С., Shiriaev, E. M., Ширяев, Е. М.
Формат:	Статья
Язык:	English
Опубликовано:	Springer Science and Business Media Deutschland GmbH 2024
Темы:	Cryptography Matrix transposition Machine learning Neural networks
Online-ссылка:	https://dspace.ncfu.ru/handle/123456789/29360
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!

id	ir-123456789-29360
record_format	dspace
spelling	ir-123456789-293602024-12-11T09:29:17Z Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks Bezuglova, E. S. Безуглова, Е. С. Shiriaev, E. M. Ширяев, Е. М. Cryptography Matrix transposition Machine learning Neural networks In this paper, the presented method, applied to transpose densified weight matrices, involves tenth machine learning when moving from feedforward to backpropagation. The algorithm is based on the diagonal matrix construction method. The process of manufacturing change will significantly increase the number of operations using technology, especially in the ten linear transformations. The number of multiplications required for linear transformations depends on the dimensionality of the input and output data, but these differences are taken into account during the training process, which includes both forward and back propagation. The proposed method leads to improved training efficiency and computational efficiency in contextual machine learning. 2024-12-11T09:28:35Z 2024-12-11T09:28:35Z 2024 Статья Bezuglova, E., Shiriaev, E. Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks // Lecture Notes in Networks and Systems. - 2024. - 1207 LNNS. - pp. 24-30. - DOI: 10.1007/978-3-031-77229-0_4 https://dspace.ncfu.ru/handle/123456789/29360 en Lecture Notes in Networks and Systems application/pdf Springer Science and Business Media Deutschland GmbH
institution	СКФУ
collection	Репозиторий
language	English
topic	Cryptography Matrix transposition Machine learning Neural networks
spellingShingle	Cryptography Matrix transposition Machine learning Neural networks Bezuglova, E. S. Безуглова, Е. С. Shiriaev, E. M. Ширяев, Е. М. Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks
description	In this paper, the presented method, applied to transpose densified weight matrices, involves tenth machine learning when moving from feedforward to backpropagation. The algorithm is based on the diagonal matrix construction method. The process of manufacturing change will significantly increase the number of operations using technology, especially in the ten linear transformations. The number of multiplications required for linear transformations depends on the dimensionality of the input and output data, but these differences are taken into account during the training process, which includes both forward and back propagation. The proposed method leads to improved training efficiency and computational efficiency in contextual machine learning.
format	Статья
author	Bezuglova, E. S. Безуглова, Е. С. Shiriaev, E. M. Ширяев, Е. М.
author_facet	Bezuglova, E. S. Безуглова, Е. С. Shiriaev, E. M. Ширяев, Е. М.
author_sort	Bezuglova, E. S.
title	Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks
title_short	Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks
title_full	Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks
title_fullStr	Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks
title_full_unstemmed	Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks
title_sort	development of an approach to confidential learning with errors in the design of neural networks
publisher	Springer Science and Business Media Deutschland GmbH
publishDate	2024
url	https://dspace.ncfu.ru/handle/123456789/29360
work_keys_str_mv	AT bezuglovaes developmentofanapproachtoconfidentiallearningwitherrorsinthedesignofneuralnetworks AT bezuglovaes developmentofanapproachtoconfidentiallearningwitherrorsinthedesignofneuralnetworks AT shiriaevem developmentofanapproachtoconfidentiallearningwitherrorsinthedesignofneuralnetworks AT širâevem developmentofanapproachtoconfidentiallearningwitherrorsinthedesignofneuralnetworks
_version_	1842245810866094080

Development of an Approach to Confidential Learning with Errors in the Design of Neural Networks

Схожие документы