Kazan Federal University Digital Repository

Reduction of the dimension of neural network models in problems of pattern recognition and forecasting

Show simple item record

dc.contributor.author Nasertdinova A.
dc.contributor.author Bochkarev V.
dc.date.accessioned 2018-04-05T07:09:59Z
dc.date.available 2018-04-05T07:09:59Z
dc.date.issued 2017
dc.identifier.issn 1742-6588
dc.identifier.uri http://dspace.kpfu.ru/xmlui/handle/net/130114
dc.description.abstract © Published under licence by IOP Publishing Ltd. Deep neural networks with a large number of parameters are a powerful tool for solving problems of pattern recognition, prediction and classification. Nevertheless, overfitting remains a serious problem in the use of such networks. A method of solving the problem of overfitting is proposed in this article. This method is based on reducing the number of independent parameters of a neural network model using the principal component analysis, and can be implemented using existing libraries of neural computing. The algorithm was tested on the problem of recognition of handwritten symbols from the MNIST database, as well as on the task of predicting time series (rows of the average monthly number of sunspots and series of the Lorentz system were used). It is shown that the application of the principal component analysis enables reducing the number of parameters of the neural network model when the results are good. The average error rate for the recognition of handwritten figures from the MNIST database was 1.12% (which is comparable to the results obtained using the "Deep training" methods), while the number of parameters of the neural network can be reduced to 130 times.
dc.relation.ispartofseries Journal of Physics: Conference Series
dc.title Reduction of the dimension of neural network models in problems of pattern recognition and forecasting
dc.type Conference Paper
dc.relation.ispartofseries-issue 1
dc.relation.ispartofseries-volume 929
dc.collection Публикации сотрудников КФУ
dc.source.id SCOPUS17426588-2017-929-1-SID85039072328


Files in this item

This item appears in the following Collection(s)

  • Публикации сотрудников КФУ Scopus [24551]
    Коллекция содержит публикации сотрудников Казанского федерального (до 2010 года Казанского государственного) университета, проиндексированные в БД Scopus, начиная с 1970г.

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics