完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Chen, C. L. Philip | en_US |
dc.contributor.author | Wang, Jing | en_US |
dc.contributor.author | Wang, Chi-Hsu | en_US |
dc.contributor.author | Chen, Long | en_US |
dc.date.accessioned | 2014-12-08T15:36:57Z | - |
dc.date.available | 2014-12-08T15:36:57Z | - |
dc.date.issued | 2014-10-01 | en_US |
dc.identifier.issn | 2162-237X | en_US |
dc.identifier.uri | http://dx.doi.org/10.1109/TNNLS.2014.2306915 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/25350 | - |
dc.description.abstract | A traditional neuro-fuzzy system is transformed into an equivalent fully connected three layer neural network (NN), namely, the fully connected neuro-fuzzy inference systems (F-CONFIS). The F-CONFIS differs from traditional NNs by its dependent and repeated weights between input and hidden layers and can be considered as the variation of a kind of multilayer NN. Therefore, an efficient learning algorithm for the F-CONFIS to cope these repeated weights is derived. Furthermore, a dynamic learning rate is proposed for neuro-fuzzy systems via F-CONFIS where both premise (hidden) and consequent portions are considered. Several simulation results indicate that the proposed approach achieves much better accuracy and fast convergence. | en_US |
dc.language.iso | en_US | en_US |
dc.title | A New Learning Algorithm for a Fully Connected Neuro-Fuzzy Inference System | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1109/TNNLS.2014.2306915 | en_US |
dc.identifier.journal | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | en_US |
dc.citation.volume | 25 | en_US |
dc.citation.issue | 10 | en_US |
dc.citation.spage | 1741 | en_US |
dc.citation.epage | 1757 | en_US |
dc.contributor.department | 電機資訊學士班 | zh_TW |
dc.contributor.department | Undergraduate Honors Program of Electrical Engineering and Computer Science | en_US |
dc.identifier.wosnumber | WOS:000343704900001 | - |
dc.citation.woscount | 0 | - |
顯示於類別: | 期刊論文 |