頁籤選單縮合
題 名 | A Learning-theoretic Approach to Model-set Identification |
---|---|
作 者 | Oishi,Yasuaki; Kimura,Hidenori; | 書刊名 | Asian Journal of Control |
卷 期 | 3:1 2001.03[民90.03] |
頁 次 | 頁10-20 |
分類號 | 448.942 |
關鍵詞 | Model-set identification; Agnostic learning theory; Law of large numbers; Sample complexity; Robust control; |
語 文 | 英文(English) |
英文摘要 | A new approach to model-set identification is proposed based on an agnostic learning theory. The squared prediction error is estimated together with its uncertainty uniformly in some parameter region. Based on this estimation, a model set is constructed so as to include the best model. The proposed approach does not require assumptions on the true dynamics or the noise, neither does it need infinite number of input-output data in order to justify its result. But it guarantees that the size of the identified model set converges to zero as the number of input-output data increases. Improvement of the precision is considered on the proposed identification method. Generalization of the approach is discussed and a numerical example is presented. |
本系統中英文摘要資訊取自各篇刊載內容。