完整後設資料紀錄
DC 欄位語言
dc.contributor.author陳宏彥en_US
dc.contributor.authorChen, Hung-Yenen_US
dc.contributor.author鄧清政en_US
dc.contributor.authorChing-Cheng Tengen_US
dc.date.accessioned2014-12-12T02:17:08Z-
dc.date.available2014-12-12T02:17:08Z-
dc.date.issued1996en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#NT850327032en_US
dc.identifier.urihttp://hdl.handle.net/11536/61687-
dc.description.abstract在本論文中,我們使用遺傳基因法和倒傳遞法來訓練模糊神經網路做函數 的近似.遺傳基因法和倒傳遞法是用來調模糊神經網路的參數.傳統條模糊 神經網路參數的方法(倒傳遞法)有個弱點就是必須依靠初使條件(連線出 始化或非連線出始化).為了解決這問題我們使用遺傳基因法和到傳遞法來 調模糊神經網路的參數. In this thesis, we present a fuzzy neural network system for a function approximation, which is trained by genetic algorithms and back propagation.The genetic algorithms and back propagation are used for tuning the FNN model parameters. The conventional method(back propagation) has a weak point that the structure of FNN model depends on initial conditions(on-line or of-line initialization).In order to solve this problem this paper proposes a tuning method for the FNN model by GA and BP.zh_TW
dc.language.isozh_TWen_US
dc.subject遺傳基因法zh_TW
dc.subject倒傳遞法zh_TW
dc.subject模糊神經zh_TW
dc.subject函數近似zh_TW
dc.subjectGenetic Algorithmsen_US
dc.subjectBack Propagationen_US
dc.subjectFuzzy Neuralen_US
dc.subjectFunction Approximationen_US
dc.title使用遺傳基因法和倒傳遞法來訓練模糊神經網路做函數的近似zh_TW
dc.titleUse of Genetic Algorithms with Back Propagation in Training of Fuzzy Neural Network for a Function Approximationen_US
dc.typeThesisen_US
dc.contributor.department電控工程研究所zh_TW
顯示於類別:畢業論文