Two Ways of using Artifiial Neural Networks in Knowledge Discovery from Chemical Materials Data

0348388 - ÚI 2011 RIV SK eng C - Conference Paper (international conference)
Holeňa, Martin
Two Ways of using Artifiial Neural Networks in Knowledge Discovery from Chemical Materials Data.
Information Technologies - Applications and Theory. Seňa: Pont, 2010 - (Pardubská, D.), s. 17-24. ISBN 978-80-970179-4-1.
[ITAT 2010. Conference on Theory and Practice of Information Technologies. Smrekovica (SK), 21.09.2010-25.09.2010]
R&D Projects: GA ČR GA201/08/1744
Institutional research plan: CEZ:AV0Z10300504
Keywords : knowledge discovery from data * chemical data mining * artificial neural networks * rules extraction * surrogate modelling
Subject RIV: IN - Informatics, Computer Science

In the application area of chemical materials, data mining methods have been used for more than a decade. By far most popular have from the very beginning been methods based on artificial neural networks. However, they are frequently used without awareness of the difference between the numeric nature of knowledge obtained from data by neural network regression, and the symbolic nature of knowledge obtained by some other data mining methods. This paper explains that within the surrogate modelling approach, which plays an important role in this area, using numeric knowledge is justified. At the same time, it recalls the possibility to obtain symbolic knowledge from neural networks in the form of logical rules and describes a recently proposed method for the extraction of Boolean rules in disjunctive normal form. Both ways of using neural networks are illustrated on examples from this application area.
Permanent Link: http://hdl.handle.net/11104/0188936