Classifying neural networks and methods of their illogical behaviour revealing

Grigoryeva, N. Yu.; Zhangirov, T. R.; Perkov, A. S.; Ivanova, Sofia A.; Liss, A. A.

doi:10.1088/1742-6596/1352/1/012024

Cited by 2 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is followed by Cluster (4,9) and Cluster (5, 9) comes as the third. A hundred or more companies are also concentrated in Clusters (6, 10), (5,10), (2,6), (3,8) and (1,6). The in the Austrian transport sector.…”

Section: Resultsmentioning

confidence: 99%

“…Clusters (10,2), (9, 2), (8, 1), (9, 3), (8, 2) (9, 1) and (8,3) show much lower values of the average total assets, however, still higher above the average.…”

Section: A36mentioning

confidence: 95%

“…The third production factor, human labour, is impossible to keep on store, thus it cannot be measured before the moment of consumption. The figure shows a very high value of average assets in Cluster (10,1).…”

Section: A36mentioning

confidence: 98%

“…remaining clusters show a considerably lower number of companies. By the same token, note that only one cluster of the Kohonen map remains unoccupied, namely Cluster (10,8). Several clusters are formed by a single company: (1, 10), (8, 2), (9, 1), (9, 3) a (10,10).…”

Section: Analysis Of Average Valuesmentioning

confidence: 98%

“…One of disadvantages of networks is that they require high data quality and possibility of illogical behaviour of the artificial neural network [9]. According to Grigoryev et al [10], this illogical behaviour can be explained by the fact that a trained ANN classifies the observations according to its own criteria, which differ from the usual criteria used by humans. Therefore, using these unusual criteria, ANN can make fundamental errors in the non-standard irregular situations.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Analysis of Transportation Companies in the Czech Republic by the Kohonen Networks - Identification of Industry Leaders

Horák¹,

Šuleř²,

Vrbka³

2021

Komunikácie

View full text Add to dashboard Cite

Computational models of artificial neural networks are currently used in different areas. Accuracy of results exceeds the performance of traditional statistical techniques. Artificial neural networks as the Kohonen map may be used e.g. to identify industry leaders, thus replacing the traditional cluster analysis and other methods. The aim of this contribution is to analyse the transportation industry in the Czech Republic by the Kohonen networks and identify industry leaders. The data file contains results - division of companies into a total of 100 clusters. Each cluster is subjected to analysis of absolute indicators and several parameters, average, as well as absolute, are examined. In total, 88 firms may be considered as industry leaders. Consequently, a fairly small group of companies has a strong influence on development of the whole transportation industry in the Czech Republic.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Clusters (10,2), (9, 2), (8, 1), (9, 3), (8, 2) (9, 1) and (8,3) show much lower values of the average total assets, however, still higher above the average.…”

Section: A36mentioning

confidence: 95%

Section: A36mentioning

confidence: 98%

Section: Analysis Of Average Valuesmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Analysis of Transportation Companies in the Czech Republic by the Kohonen Networks - Identification of Industry Leaders

Horák¹,

Šuleř²,

Vrbka³

2021

Komunikácie

View full text Add to dashboard Cite

show abstract

Specific features of feed-forward neural networks application in classification and regression problems in algology

Grigoryeva

Zhangirov

Liss

2020

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Abundance and biological diversity of phytoplankton communities, investigated in this work, are often used as a marker for the determination of environmental health and fresh water quality. Presently their routine analysis is very time consuming and expensive. A lot of articles are devoted to the development of a system for an in situ automated analysis of phytoplankton properties. However, the applied problems of biology, ecology and, in particular, algology usually are associated with some difficulties due to shortage and/or fuzziness of the experimental data. Hence, while using neural network modelling a set of specific problems can occur. In this article on the base of experimental data several such problems are presented and possible solutions are suggested. In particular, the illogical behavior of classifying neural network is revealed, while studying the biological diversity of cyanobacteria, and the original technique for results validation is presented. This problem is investigated on a set of spectroscopic data, recorded by means of confocal laser scanning microscopy. The generalization quality of the trained model is studied as the main learning parameter. Another problem of shortage dataset is examined in the frames of regression model for bioplankton abundance. This problem is solved by means of feed-forward back-propagation neural networks with two hidden layers. The modelling was carried out on a small experimental selection (only 39 observations were available), despite this, the relatively high determination coefficient was obtained for the training and test samples, while using dropout layout.

show abstract

Classifying neural networks and methods of their illogical behaviour revealing

Cited by 2 publications

References 7 publications

Analysis of Transportation Companies in the Czech Republic by the Kohonen Networks - Identification of Industry Leaders

Analysis of Transportation Companies in the Czech Republic by the Kohonen Networks - Identification of Industry Leaders

Specific features of feed-forward neural networks application in classification and regression problems in algology

Contact Info

Product

Resources

About