Stabilizing the convergence of online-learning in Neuro-fuzzy systems by an immune system-inspired approach
Autor(en): | Brockmann, W. Horst, A. |
Stichwörter: | Adaptive control systems; Adaptive systems; Chaos theory; Control systems; Education; Fuzzy logic; Fuzzy systems; Knowledge based systems; Learning systems; Online systems, A-priori; Adaptive learning systems; Closed loops; Control applications; Dynamic learning; Function approximators; Immune systems; International conferences; Knowledge-based; Neuro-fuzzy systems; Process modelling; Safety-critical; Speed ups; Suboptimal controls; System characteristics, Chaotic systems | Erscheinungsdatum: | 2007 | Journal: | IEEE International Conference on Fuzzy Systems | Zusammenfassung: | Adaptive learning systems are needed in many control applications. Neuro-fuzzy systems are very useful here because they are universal function approximators and do not require a formal process model. Furthermore, they allow incorporating a priori knowledge to speed up convergence or to treat safety-critical situations. But learning in a closed loop setup may nevertheless lead to a truly chaotic systems behaviour because what is learned has in impact on what is learned next, and so forth. Hence an arbitrary control behaviour may emerge dynamically, thus leading to an allowed, but suboptimal control behaviour or learning result, respectively. The dynamic learning process thus has to be guided, in order to avoid such unwanted system characteristics. This is the aim of the SILKE-approach (System to Immunize Learning Knowledge-based Elements). This paper describes its basic concept and presents some first results. © 2007 IEEE. |
Beschreibung: | Conference of 2007 IEEE International Conference on Fuzzy Systems, FUZZY ; Conference Date: 23 July 2007 Through 26 July 2007; Conference Code:73106 |
ISBN: | 9781424412105 | ISSN: | 10987584 | DOI: | 10.1109/FUZZY.2007.4295391 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-50249149885&doi=10.1109%2fFUZZY.2007.4295391&partnerID=40&md5=89545f4f875b80cdb517ab31729f0c7c |
Show full item record