Поиск по всему репозиторию:

Показать краткое описание

dc.contributor.authorGolovko, Vladimir
dc.contributor.authorKroshchanka, Aliaksandr
dc.contributor.authorTurchenko, Volodymyr
dc.contributor.authorJankowski, Stanislaw
dc.contributor.authorTreadwell, Douglas
dc.coverage.spatialWarsawru_RU
dc.date.accessioned2023-11-01T12:11:41Z
dc.date.available2023-11-01T12:11:41Z
dc.date.issued2015
dc.identifier.citationA New Technique for Restricted Boltzmann Machine Learning / A. Kroshchanka [et. al] // Proceedings of the 8th IEEE International Conference IDAACS-2015, Warsaw, September 24-26, 2015 / Information Science Warsaw University of Technology. – Warsaw, 2015. – P. 182–186. – Bibliogr.: p. 186 (9 titles).ru_RU
dc.identifier.urihttps://rep.bstu.by/handle/data/36748
dc.descriptionГоловко Владимир, Крощенко Александр, Турченко Владимир, Янковский Станислав, Тредуэлл Дуглас. Новая методика ограниченного машинного обучения по Больцмануru_RU
dc.description.abstractOver the last decade, deep belief neural networks have been a hot topic in machine learning. Such networks can perform a deep hierarchical representation of input data. The first layer can extract low-level features, the second layer can extract high-level features and so on. In general, deep belief neural network represents manylayered perceptron and permits to overcome some limitations of conventional multilayer perceptron due to deep architecture. In this work we propose a new training technique called Reconstruction Error-Based Approach (REBA) for deep belief neural network based on restricted Boltzmann machine. In contrast to classical Hinton’s training approach, which is based on a linear training rule, the proposed technique is based on a nonlinear learning rule. We demonstrate the performance of REBA technique for the MNIST dataset visualization. The main contribution of this paper is a novel view on the training of a restricted Boltzmann machine.ru_RU
dc.language.isoenru_RU
dc.publisherInformation Science Warsaw University of Technologyru_RU
dc.subjectrestricted Boltzmann machineru_RU
dc.subjectограниченная машина Больцманаru_RU
dc.subjectdeep learningru_RU
dc.subjectглубокое обучениеru_RU
dc.subjectdata visualizationru_RU
dc.subjectвизуализация данныхru_RU
dc.subjectmachine learningrru_RU
dc.subjectмашинное обучениеru_RU
dc.titleA New Technique for Restricted Boltzmann Machine Learningru_RU
dc.title.alternativeНовая методика ограниченного машинного обучения по Больцмануru_RU
dc.typeСтатья (Article)ru_RU


Файлы в этом документе

Thumbnail

Данный элемент включен в следующие коллекции

Показать краткое описание