國立中央大學產業經濟研究所; 國立臺灣大學經濟學系Graduate Institute of Industrial Economics, National Central University; Department of Economics, National Taiwan University張明宗朱敬一林向愷Chang, M.C.M.C.ChangChu, C.Y.C.Y.ChuLin, S.K.S.K.Lin2017-09-082018-06-282017-09-082018-06-281997-12http://ntur.lib.ntu.edu.tw//handle/246246/282209相對於最小平方學習機能，本文所提出的最小預測誤差學習機能的特色是考慮了經濟個體的決策會影響到他所估計的參數值。由於考慮了這種訊息回饋，這個學習機能的目標函數具備了Lyapunov函數的性質。因此,我們可以用它來分析大域穩定。最後，我們並以Bray(1982)的模型說明訊息回饋的重要性。In this paper, we propose the minimum prediction error learning algorithm with information feedback as an alternative to the leastsquare learning algorithm. Once the proposed algorithm allows for information feedback, the objective function in the algorithm satisfied the properties of the Lyapunov function. Hence, one can use it to study the stability of the model in the large. Finally, we use the Bray's (1982) model to illustrate the importance of information feedback in the proposed algorithm.159 bytestext/html最小預測誤差學習機能訊息回饋常微分方程方法Minimum prediction error learningInformation feedbackOrdinary differential equation approachjournal articlehttp://ntur.lib.ntu.edu.tw/bitstream/246246/282209/1/index.html