Classifying neural networks and methods of their illogical behaviour revealing

Autor:	S. A. Ivanova, T. R. Zhangirov, A. S. Perkov, A. A. Liss, N. Y. Grigoryeva
Rok vydání:	2019
Předmět:	Visualization methods History Artificial neural network Generalization business.industry Computer science Feed forward Artificial intelligence Representation (mathematics) business Backpropagation artificial neural network Computer Science Applications Education
Zdroj:	Journal of Physics: Conference Series. 1352:012024
ISSN:	1742-6596 1742-6588
DOI:	10.1088/1742-6596/1352/1/012024
Popis:	In this article a feedforward error backpropagation artificial neural network is investigated and the analysis of its illogical behaviour is presented. The problem of illogical behavior arises in various models of artificial neural networks. In the presented work a classifying artificial neural network (CANN) is considered and several learning algorithms were implemented and compared. CANN was designed for automatic differentiaition of cyanobacterial strains during environmental monitoring and some of trained networks demonstrated illogical behavior in further testing. Several original techniques were elaborated for estimation of the quality and accuracy of classification in addition to the traditional ones. Novel visualization methods were suggested for classification and generalization results representation.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::0528ee6d9467878de78ebfcbd84d3dba https://doi.org/10.1088/1742-6596/1352/1/012024 Zobrazit plný text záznamu