關鍵字查詢 | 類別:會議論文 | | 關鍵字:USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS

[第一頁][上頁]1[次頁][最末頁]目前在第 1 頁 / 共有 04 筆查詢結果
序號 學年期 教師動態
1 83/1 電機系 蕭敏男 講師 會議論文 發佈 USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS , [83-1] :USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS會議論文USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS由類神經網路建立中文四聲辨認專家系統Su, Mu-Cbun; Hsieh, Ching-Tang; Shiau, Min-Nan淡江大學電機工程學系Neural Network;Fuzzy Systems;Speech Recognition;Machine Learning臺北市:中國模糊學會中華民國第二屆模糊理論與應用研討會論文集=1994 Second National Conference on Fuzzy Theory and Applications (Fuzzy 1994),頁423-428臺灣大學機械系; 臺灣工業技術學院電機系在大多數的專家系統中,無論是Crispy 或Fuzzy 的if-then 式的規則,大致上都是從人類專家口語上的敘述而得。然而,這些初始的口語規則是非常地籠統(雖然定性上是正確的) ,仍需進一步修改以達到更好的效果;因此設計專家系統的關鍵所在,就是如何從一 組資料中萃取出適當的規則來。這篇論文探討如何藉訓練類神經網路來解決這種規則萃取的問題。在經過充份的訓練之後,網路上的參數可被用來建立Cr ispy 和Fuzzy 的if-then規則。本論文的觀點及方法,是以一個連續的中文四聲辨認問題作為例證。;In most of expert systems, crispy or fuzzy if-then rules are generally derived from human experts using linguistic information. However, the initial linguistic rules are invariably rather crude and, although qualitatively correct, need to be refined to achieve better performance. Therefore the major issue in designing an
2 83/1 電機系 謝景棠 教授 會議論文 發佈 USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS , [83-1] :USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS會議論文USE OF NEURAL NETWORKS AS CHINESE FOUR TONE RECOGNITION EXPERT SYSTEMS由類神經網路建立中文四聲辨認專家系統Su, Mu-Cbun; Hsieh, Ching-Tang; Shiau, Min-Nan淡江大學電機工程學系Neural Network;Fuzzy Systems;Speech Recognition;Machine Learning臺北市:中國模糊學會中華民國第二屆模糊理論與應用研討會論文集=1994 Second National Conference on Fuzzy Theory and Applications (Fuzzy 1994),頁423-428臺灣大學機械系; 臺灣工業技術學院電機系在大多數的專家系統中,無論是Crispy 或Fuzzy 的if-then 式的規則,大致上都是從人類專家口語上的敘述而得。然而,這些初始的口語規則是非常地籠統(雖然定性上是正確的) ,仍需進一步修改以達到更好的效果;因此設計專家系統的關鍵所在,就是如何從一 組資料中萃取出適當的規則來。這篇論文探討如何藉訓練類神經網路來解決這種規則萃取的問題。在經過充份的訓練之後,網路上的參數可被用來建立Cr ispy 和Fuzzy 的if-then規則。本論文的觀點及方法,是以一個連續的中文四聲辨認問題作為例證。;In most of expert systems, crispy or fuzzy if-then rules are generally derived from human experts using linguistic information. However, the initial linguistic rules are invariably rather crude and, although qualitatively correct, need to be refined to achieve better performance. Therefore the major issue in designing an
3 82/1 電機系 謝景棠 教授 會議論文 發佈 Use of neural networks as Chinese four tone recognition expert systems , [82-1] :Use of neural networks as Chinese four tone recognition expert systems會議論文Use of neural networks as Chinese four tone recognition expert systems謝景棠; Hsieh, Ching-tang; 蘇木春; Su, Mu-chun淡江大學電機工程學系1994 Second national conference on fuzzy theory and applicationstku_id:000073063; 000095024;Made available in DSpace on 2010-01-11T08:17:17Z (GMT). No. of bitstreams: 0en<links><record><name>機構典藏連結</name><url>http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/38961</url></record></links>
4 82/1 電機系 蘇木春 教授 會議論文 發佈 Use of neural networks as Chinese four tone recognition expert systems , [82-1] :Use of neural networks as Chinese four tone recognition expert systems會議論文Use of neural networks as Chinese four tone recognition expert systems謝景棠; Hsieh, Ching-tang; 蘇木春; Su, Mu-chun淡江大學電機工程學系1994 Second national conference on fuzzy theory and applicationstku_id:000073063; 000095024;Made available in DSpace on 2010-01-11T08:17:17Z (GMT). No. of bitstreams: 0en<links><record><name>機構典藏連結</name><url>http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/38961</url></record></links>
[第一頁][上頁]1[次頁][最末頁]目前在第 1 頁 / 共有 04 筆查詢結果