Kohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks

Convolutional neural networks have become one of the most powerful computing tools of artificial intelligence in recent years. They are especially suitable for the analysis of images and other data that have an inherent sequence structure, such as time series data. In the case of data in the form of...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Michał Bereta
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	kohonen network convolutional neural network multiple input neural networks Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/6ee391cf058242b9989f09627f94bd96
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6ee391cf058242b9989f09627f94bd96
record_format	dspace
spelling	oai:doaj.org-article:6ee391cf058242b9989f09627f94bd962021-11-11T19:11:57ZKohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks10.3390/s212172211424-8220https://doaj.org/article/6ee391cf058242b9989f09627f94bd962021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7221https://doaj.org/toc/1424-8220Convolutional neural networks have become one of the most powerful computing tools of artificial intelligence in recent years. They are especially suitable for the analysis of images and other data that have an inherent sequence structure, such as time series data. In the case of data in the form of vectors of features, the order of which does not matter, the use of convolutional neural networks is not justified. This paper presents a new method of representing non-sequential data as images that can be analyzed by a convolutional network. The well-known Kohonen network was used for this purpose. After training on non-sequential data, each example is represented by so-called U-image that can be used as input to a convolutional layer. A hybrid approach was also presented, where the neural network uses two types of input signals, both U-image representation and the original features. The results of the proposed method on traditional machine learning databases as well as on a difficult classification problem originating from the analysis of measurement data from experiments in particle physics are presented.Michał BeretaMDPI AGarticlekohonen networkconvolutional neural networkmultiple input neural networksChemical technologyTP1-1185ENSensors, Vol 21, Iss 7221, p 7221 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	kohonen network convolutional neural network multiple input neural networks Chemical technology TP1-1185
spellingShingle	kohonen network convolutional neural network multiple input neural networks Chemical technology TP1-1185 Michał Bereta Kohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks
description	Convolutional neural networks have become one of the most powerful computing tools of artificial intelligence in recent years. They are especially suitable for the analysis of images and other data that have an inherent sequence structure, such as time series data. In the case of data in the form of vectors of features, the order of which does not matter, the use of convolutional neural networks is not justified. This paper presents a new method of representing non-sequential data as images that can be analyzed by a convolutional network. The well-known Kohonen network was used for this purpose. After training on non-sequential data, each example is represented by so-called U-image that can be used as input to a convolutional layer. A hybrid approach was also presented, where the neural network uses two types of input signals, both U-image representation and the original features. The results of the proposed method on traditional machine learning databases as well as on a difficult classification problem originating from the analysis of measurement data from experiments in particle physics are presented.
format	article
author	Michał Bereta
author_facet	Michał Bereta
author_sort	Michał Bereta
title	Kohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks
title_short	Kohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks
title_full	Kohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks
title_fullStr	Kohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks
title_full_unstemmed	Kohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks
title_sort	kohonen network-based adaptation of non sequential data for use in convolutional neural networks
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/6ee391cf058242b9989f09627f94bd96
work_keys_str_mv	AT michałbereta kohonennetworkbasedadaptationofnonsequentialdataforuseinconvolutionalneuralnetworks
_version_	1718431590214795264

Kohonen Network-Based Adaptation of Non Sequential Data for Use in Convolutional Neural Networks

Ejemplares similares