動態輻狀基底函數類神經網路建構之研究

Abstract

近年來輻狀基底函數類神經網路 (Radial Basis Function Networks , RBFN) 應用在時間序列相關問題上已有相當的成果。在這篇論文裡，我們嘗試建構一個電腦軟體工具，可以很容易造出 RBFN，應用在時間序列預測相關問題上。更進一步的說，我們的電腦工具可以輕易做出即時修正，完全符合使用者的需求。我們一開始先複習 RBFN 的基本架構， 並說明如何應用到時間序列的問題上。接著我們研究近年來相當受到重視的 T-RBF (Temporal RBF) 架構。最後，我們解釋如何使用 Adobe Flex 去建構我們所需要的電腦軟體工具。這個工具是跨平台的程式，並且不論是雲端計算或是單機應用皆很合適。

During recent years, applying Radial Basis Function Networks (RBFN) to \ntime series problems yields many important results. In this thesis, we \ntry to implement a cross-platform computer tool that can easily \nconstruct a RBFN applied to time series forecasting problems. Moreover, \nthe RBFN created by this computer tool can do real-time modification \nto fit specific needs. We first review the basic structures of RBFN \nand explain how it can be applied to time series problems. Then, we \nsurvey on so called temporal radial basis function (T-RBF) model, \nwhich draws much attention these years. Finally, we explain how we \nuse Adobe Flex to create a computer tool as we mentioned in the \nbeginning. The computer application is cross-platform and is suitable \nfor both cloud computing and desktop applications.