查詢結果分析
來源資料
相關文獻
- Fuzzy Neural Network Control of Nonlinear Systems
- Reinforcement Learning for Ga-Based Neural Networks
- 應用模糊類神經網路於微電網電壓穩定控制
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
- 臺灣汽保費率之估計--對數線性費率模式與類神經網路之比較
頁籤選單縮合
題 名 | Fuzzy Neural Network Control of Nonlinear Systems=非線性系統之糢糊類神經網路控制 |
---|---|
作 者 | 林正堅; | 書刊名 | 南開學報 |
卷 期 | 1 1996.06[民85.06] |
頁 次 | 頁111-130 |
分類號 | 312.2 |
關鍵詞 | 糢糊控制; 類神經網路; 加強式學習; 歸屬函數; Fuzzy control; Neural network; Reinforcenent learning; Membership function; |
語 文 | 英文(English) |
中文摘要 | 本文題出一糢糊適應性學習控制網路來實現糢糊邏輯控制系統。一種線上之架構 及參數學習演算法能夠線上分割輸入及輸出空間,調整歸屬函數,及找到適當地糢糊邏輯法 則。此種學習方法在過程中需要有準確之訓練資料。而在一些實際的應用中,準確之訓練資 料可能無法得到,所以我們亦提出加強式糢糊適應性學習控制網路來解決此一問題,藉由結 合線上之架構及參數學習演算法、時間差法及隨機搜尋法來完成。 |
英文摘要 | A Fuzzy Adaptive Learning COntrol Network (FALCON) is proposed for the realization of a fuzzy logie control system. An on-line structure/parameter learning algorithm, called FALCON-ART, can on-line partition the input/output spaces, tune membership functions and find proper fuzzy logic rules dynamically without any a prior knowledge or even any initial information on these. The FALCON-ART requires exact supervised training data for learning. In some real-time applicatins. exact training data may be expensive or even impossible to obtain. To solve this problem, a Reinforcement Fuzzy Adaptive Learning COntrol Network (RFALCON) is further proposed. By combiming a proposed on-line supervised structure/parameter learning technique, the temporal difference method, and the stochastic exploratory algorithm. a on-line supervised structure/parameter learning algorithm called RFALCON-ART, is proposed for constructing the RFALCON dynamically. |
本系統中英文摘要資訊取自各篇刊載內容。