Full metadata record
DC FieldValueLanguage
dc.contributor.author張俊隆en_US
dc.contributor.authorChun-Lung Changen_US
dc.contributor.author林進燈en_US
dc.contributor.authorChin-Teng Linen_US
dc.date.accessioned2014-12-12T02:09:06Z-
dc.date.available2014-12-12T02:09:06Z-
dc.date.issued2005en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#GT008812803en_US
dc.identifier.urihttp://hdl.handle.net/11536/55779-
dc.description.abstract無論從應用或生物觀點,使用一組平行的細胞神經網路(cellular neural networks, CNN)以完成高階資訊處理與推論能力已被廣泛的接受。如此的整合型細胞神經網路可以解決比較複雜的問題。本論文提出一種以遞迴式模糊神經網路(recurrent fuzzy neural network)的架構以自動建構CNN整合系統。這個稱為RFCNN/RFCCNN (recurrent fuzzy CNN/ recurrent fuzzy coupled CNN)的整合系統可以同時自動的學習CNN的網路結構與參數。其網路結構學習包括模糊規則(fuzzy rules)與CNN數目的建立;其參數學習包括模糊歸屬函數與CNN模板(template)參數的學習。在RFCNN/RFCCNN中,每個模糊規則對應一個CNN。一個新的線上適應獨立元件分析混合模型(on-line adaptive ICA (independent component analysis) mixture-model technique)技術被提出以做為RFCNN的結構學習;另外,次序微分(ordered-derivative)可做為RFCNN/RFCCNN的參數學習。本論文所提出RFCNN/RFCCNN對於既存CNN整合系統同時地建立模糊規則與學習CNN模板參數的兩難提供一個解決方案。本論文最後並以工業上瑕疵檢測的問題做為說明RFCNN/RFCCNN系統的能力,實驗結果顯示所提出的方法是有效且有潛力的。zh_TW
dc.description.abstractIt is widely accepted that using a set of cellular neural networks (CNNs) in parallel can achieve higher-level information processing and reasoning functions either from application or biologics points of views. Such an integrated CNN system can solve more complex intelligent problems. In this thesis we propose two novel frameworks for automatically constructing a multiple-CNN integrated neural system in the form of a recurrent fuzzy neural network. The systems, called recurrent fuzzy CNN (RFCNN) and recurrent fuzzy coupled CNN (RFCCNN), can automatically learn its proper network structure and parameters simultaneously. The structure learning includes the fuzzy division of the problem domain and the creation of fuzzy rules and CNNs. The parameter learning includes the tuning of fuzzy membership functions and CNN templates. In the RFCNN/RFCCNN, each learned fuzzy rule corresponds to a CNN. Hence, each CNN takes care of a fuzzily separated problem region, and the functions of all CNNs are integrated through the fuzzy inference mechanism. A new on-line adaptive ICA (independent component analysis) mixture-model technique is proposed for the structure learning of RFCNN/RFCCNN, and the ordered-derivative calculus is applied to derive the recurrent learning rules of CNN templates in the parameter-learning phase. The proposed RFCNN/RFCCNN provides a solution to the current dilemma on the decision of templates and/or fuzzy rules in the existing integrated (fuzzy) CNN systems. The capability of the proposed RFCNN and RFCCNN are demonstrated and compared on the real-world defect inspection problems. Experimental results show that the proposed scheme is effective and promising.en_US
dc.language.isoen_USen_US
dc.subject細胞神經網路zh_TW
dc.subject模糊推論系統zh_TW
dc.subject模糊細胞神經網路zh_TW
dc.subject神經網路zh_TW
dc.subjectCellular Neural Networken_US
dc.subjectFuzzy Inference Systemen_US
dc.subjectFuzzy Cellular Neural Networken_US
dc.subjectArtificial Neural Networken_US
dc.title模糊細胞神經網路整合系統zh_TW
dc.titleA Fuzzy Cellular Neural Network Integrated Systemen_US
dc.typeThesisen_US
dc.contributor.department電控工程研究所zh_TW
Appears in Collections:Thesis


Files in This Item:

  1. 280301.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.