類神經網路為處理資料探勘問題的技術之一，其學習結果通常有較高的正確率， 且對於存有雜訊的資料有較好的容錯能力，其網路架構也能夠表達屬性間複雜的關係。 然而其學習結果為一黑箱，對於使用者缺乏解釋能力，使得類神經網路在應用上受到 一定程度的限制。本研究透過規則歸納演算法由已訓練類神經網路中擷取出明確的規 則，用以解釋類神經網路的學習結果，且所提出之規則擷取架構將能夠適用於不同的 類神經網路模式中。並於規則擷取的過程考量分類錯誤成本的影響，使所擷取之規則 能反應不同類別的分類錯誤成本更能符合實務上的需要。本研究架構以Cendmwska所 提出之PRISM演算法為規則擷取基礎，分別以Adacost、Metacost以及修改PRISM資 訊函數三種方式使所擷取之規則能考量分類錯誤成本。並將本研究方法與REFNE規 則擷取架構，以UCI_ML資料庫為評比基礎就所產生規則之規則數目、正確率以及分 類錯誤成本進行比較與分析。

Neural network, as a popular approach in data mining, usually has better learning results with relatively high accuracy. It provides good fault-tolerant ability for handling data with noises, and its network structure can also presents the complicated relationships among attributes. However, such black-boxed type of neural network process lacks the ability of explanation to offer the users with comprehensibly manageable knowledge, and the applica-tions of neural network are occasionally restricted. In this paper, a rule induction algorithm is employed to retrieve the explicit rules for interpret the learning results from neural networks. Furthermore, by considering the misclassification costs in the retrieval process, the retrieved rules would be more realistic to practical uses. The proposed approach is based on PRISM algorithm proposed by Cendrowska, and uses the methods of Adacost, Metacost, and information entropy to consider the misclassification costs. An empirical investigation is performed by utilizin g the UCI-ML database to verify the effectiveness of the proposed approach.