|
advertisement |
|
|
|
|
|
|
Industrial Automatic Control Systems and Controllers Annotation << Back
Research Adaptive Machine Learning of Artificial Neural Networks on Cloud Platform |
A.V. Ostroukh, N.O. Listov, K.A. Barinov
The paper presents the results of research for the adaptive machine learning of artificial neural networks on the Microsoft Azure cloud platform, which allows you to dynamically change the source of the training sample and provide users and/or other applications with access to the completed training network with minimal delay. Created a model of adaptive learning system using feedback. Modeling of the neural network was carried out in AnyLogic to simulate the selection of data and the evaluation of training time and MatLab to estimate the global error when using the data set that received the highest priorities in the selection. The effectiveness of the proposed adaptive learning system of artificial neural networks using feedback applied to networks solving problems with classifi ed data is shown.
Keywords: cloud computing; cloud platform; deep learning neural networks (DLNN); machine learning (ML); simulation.
Contacts: E-mail: ostroukh@mail.ru, E-mail: necron9631@yandex.ru
Pp. 23-35. |
|
|
|
Last news:
Выставки по автоматизации и электронике «ПТА-Урал 2018» и «Электроника-Урал 2018» состоятся в Екатеринбурге Открыта электронная регистрация на выставку Дефектоскопия / NDT St. Petersburg Открыта регистрация на 9-ю Международную научно-практическую конференцию «Строительство и ремонт скважин — 2018» ExpoElectronica и ElectronTechExpo 2018: рост площади экспозиции на 19% и новые формы контент-программы Тематика и состав экспозиции РЭП на выставке "ChipEXPO - 2018" |