查詢結果分析
來源資料
相關文獻
- A Self-organizing Neural-Fuzzy System for Knowledge Extraction
- 新世代人種的誕生--數位虛擬人的未來發展初探
- A Study on Automatic Incident Detection--Application of Fuzzy Sets and Neural Networks
- Modified Hamming Neural Network and Its Character Recognition System
- 多層級交換式區域網路
- 跨越官僚的專業線:網路力量與救災行動
- Stability Analysis of Takagi-Sugeno Fuzzy Systems for Neural Network with Time-Varying Delays-Delayed Decomposition Approach
- Application of Neural-fuzzy Sliding-mode Control to a Trolley Control System
- 具自我調適功能之線上課程問題自動回覆系統
- 應用模糊理論與類神經網路於數位內容文字與背景配色視認性之研究
頁籤選單縮合
題名 | A Self-organizing Neural-Fuzzy System for Knowledge Extraction=規劃式人工智能網路模糊系統 |
---|---|
作者姓名(中文) | 張珩; | 書刊名 | 華岡工程學報 |
卷期 | 8 1995.03[民84.03] |
頁次 | 頁1-11 |
分類號 | 448.94 |
關鍵詞 | 人工智能; 網路; 模糊系統; |
語文 | 英文(English) |
中文摘要 | 本文主在發展一架構步驗,能規劃學習數值數據,並使用於推理規劃之中。此項 功能是由網路神經加權與模糊系統共組而成。主要的特性在於使用多層次的數據分析與學習 ,同時減少雜訊的產生。最終結果將產生模糊規則與模糊函數。此項結果不僅指示出輸入輸 出的變數特性,同時可針對問題產生IF-THEN的輸人輸出關係。此系統經測試後,使用的計 算時間,較相似的人工神經網路快了一倍,同時使用經驗數據,也減少了專家系統中,規則 詢查繁復的工泉。此架構中,容許問題範圍擴大與規則增加,不須重組網路,訓練。只要相 對的增加神經元即可。 |
英文摘要 | This study focuses on the development of an algorithm combining self- learning and reasoning with vague numerical data sets. The algorithm derived from neural network and fuzzy system is formed to capture the empirical information commonly inherented in daily life experiences such as stock markets, various manufacturing practices, and many automated control issues. The important feature of the proposed algorithm based on multiple "reasoning" phases, is to eliminate the "noises"in the data sets and to construct a fuzzy may (Fuzzy Association Memory)for rule-based reasoning Convergence of "training "phases is much faster than the normal back-propagation algorithm used in most Artificial Neural Network calculations. It also avoids the rule-matching procedure in developing inference engine of traditional expert systems. The contribution of this work, called "memory hysteresis,"mainly resides on the expansion of antecedents with corres ponding expansion of neural nets and fuzzy maps. Therefore, the dependent antecedents can be parallelly included, and insignificant rule nodes are faded out as the network converged. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。