Number of the records: 1
Rules extraction from neural networks trained on multimedia data
- 1.
SYSNO ASEP 0512089 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Rules extraction from neural networks trained on multimedia data Author(s) Fanta, M. (CZ)
Pulc, P. (CZ)
Holeňa, Martin (UIVT-O) SAI, RIDSource Title ITAT 2019: Information Technologies – Applications and Theory. - Aachen : Technical University & CreateSpace Independent Publishing, 2019 / Barančíková P. ; Holeňa M. ; Horváth T. ; Pleva M. ; Rosa R. - ISSN 1613-0073 Pages s. 26-35 Number of pages 10 s. Publication form Online - E Action ITAT 2019: Conference Information Technologies - Applications and Theory /19./ Event date 20.09.2019 - 24.09.2019 VEvent location Donovaly Country SK - Slovakia Event type EUR Language eng - English Country DE - Germany Keywords artificial neural networks ; multilayer perceptrons ; deep networks ; rules extraction ; multimedia data Subject RIV IN - Informatics, Computer Science OECD category Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) R&D Projects GA18-18080S GA ČR - Czech Science Foundation (CSF) Institutional support UIVT-O - RVO:67985807 EID SCOPUS 85074095221 Annotation Since the universal approximation property of artificial neural networks was discovered in the late 1980s, i.e., their capability to arbitrarily well approximate nearly arbitrary relationships and dependences, a full exploitation of this property has been always hindered by the very low human-comprehensibility of the purely numerical representation that neural networks use for such relationships and dependences. The mainstream of attempts to mitigate that incomprehensibility are methods extracting, from the numerical representation, rules of some formal logic, which are in general viewed as human-comprehensible. Many dozens of such methods have already been proposed since the 1980s, differing in a number of diverse aspects. Due to that diversity, and also due to a close connection of the semantics of extracted rules to the repsective application domain, no rules extraction methods have ever become a standard, and it is always necessary to select a suitable method for the considered domain. Here, rules extraction from trained neural networks is employed for multimedia data, which is an increasingly important but also increasingly complex kind of data. Three particular rules extraction methods are considered and applied to the modalities recognized text data and the speech acoustic data, both of them with different subsets of features. A detailed comparison of the performance of the considered methods on those datasets is presented, and a statistical analysis of the obtained results is performed.
Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2020 Electronic address http://ceur-ws.org/Vol-2473/paper4.pdf
Number of the records: 1