| Mixed radix systems of fully connected neuro-fuzzy inference systems with special properties | |
| Wang J.2; Chen C.-T.2; Chen C.L.P.1; Yu Y.-Q.3 | |
| 2015-09-28 | |
| Source Publication | ICCSS 2015 - Proceedings: 2015 International Conference on Informative and Cybernetics for Computational Social Systems |
| Pages | 105-109 |
| Abstract | In this paper, based on the transformation from the fuzzy inference system into a fully connected neural network, F-CONFIS, the mixed radix systems in Fully Connected Neural Fuzzy Inference Systems are derived. The functional equivalence between a fuzzy system and a neural network has been proved, however, they are non-constructive. F-CONFIS provides constructive steps to build the equivalence between a neuro-fuzzy system and a NN. F-CONFIS differs from traditional neural networks by its special properties and can be considered as the variation of a kind of multilayer neural network. It is important to find the mixed radix systems and the properties of this new type of fuzzy neural networks properties so that the training algorithm can be properly carried out for the F-CONFIS. The simulation results indicate that the proposed approach achieves excellent performance. |
| Keyword | Fully Connected Neuro-Fuzzy System Fuzzy Logic Fuzzy Neural Networks Gradient Descent Neural Networks Neuro-Fuzzy System |
| DOI | 10.1109/ICCSS.2015.7281158 |
| URL | View the original |
| Language | 英語 |
| Fulltext Access | |
| Citation statistics | |
| Document Type | Conference paper |
| Collection | University of Macau |
| Affiliation | 1.Universidade de Macau 2.Guangdong Polytechnic Normal University 3.Guangdong University of Technology |
| Recommended Citation GB/T 7714 | Wang J.,Chen C.-T.,Chen C.L.P.,et al. Mixed radix systems of fully connected neuro-fuzzy inference systems with special properties[C],2015:105-109. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment