Publication type: Conference paper
Type of review: Peer review (publication)
Title: Can we ignore the compositional nature of compositional data by using deep learning aproaches?
Authors: Templ, Matthias
et. al: No
Proceedings: Book of Short Papers SIS 2021
Editors of the parent work: Perna, Cirna
Salvati, Nicola
Schirripa Spagnolo, Francesco
Page(s): 243
Pages to: 248
Conference details: Surface Inspection Summit Europe, Aachen, Germany, 9-10 November 2021
Issue Date: 2021
Publisher / Ed. Institution: Pearson
Publisher / Ed. Institution: London
ISBN: 9788891927361
Language: English
Subjects: Deep learning; Compositional data analysis
Subject (DDC): 006: Special computer methods
Abstract: Care must be taken not to simply apply multivariate data analysis methods to compositional data. For example, one can show that correlations are biased to be negative, and almost all statistical methods result in biased estimates when applied to compositional data. One way out is to analyze data methods from compositional data analysis, i.e. by carrying out a log-ratio analysis. This contribution has its focus on settings where only the prediction and classification error is important rather than an interpretation of results. In this setting it is well-known that classification and prediction errors are smaller with a log-ratio approach using traditional machine learning methods. However, is this also true when training a neural network who may learn the inner relationships between parts of a whole also without representing the data in log-ratios? This contribution give an indication on this matter using one real data set from chemical measurements on beers.
URI: https://it.pearson.com/content/dam/region-core/italy/pearson-italy/pdf/Docenti/Universit%C3%A0/pearson-sis-book-2021-parte-1.pdf
https://digitalcollection.zhaw.ch/handle/11475/24598
Fulltext version: Published version
License (according to publishing contract): Licence according to publishing contract
Departement: School of Engineering
Organisational Unit: Institute of Data Analysis and Process Design (IDP)
Appears in collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.