學習向量量化網路分類之模擬研究

A Simulation Study on Classified Accuracy for Learning Vector Quantization

蔡良庭(Liang-Ting Tsai) ； 楊志堅(Chih-Chien Yang)

《測驗統計年刊》 12期_下 (2004/12) Pp. 269-291

https://doi.org/10.6773/JRMS.200412.0269

摘要

本研究採電腦模擬探討不同訓練範例樣本數、學習速率及隱藏層個數對學習向量量化網路分類正確率之影響。在實驗設計上，先產生三種混合樣本資料，以比較在各種不同的實驗設計下，學習向量量化網路分類正確性之差異。結果發現不論為何種混合樣本資料，分類正確率會隨著訓練範例樣本數的增加而呈現遞增的趨勢。在學習速率方面則有一共同點為當學習速率0.1時，其模式之分類效果都是最差的；其餘學習速率的分類表現並無規則可循，亦無表現突出者。但當以不同隱藏層處理單元數進行模擬試驗所得結果，以隱藏層個數為2時，分類正確率都是最佳的。

關鍵字

類神經網路 ； 學習向量量化網路 ； 截尾常態分配

並列摘要

The purpose of this study was to explore the effect of the different training samples, learning rate and numbers of hidden layers on the classified accuracy when using Learning vector Quantization to analysis. When the number of the training samples were on the two numbers, 200 and 250, the classified accuracy was irregular, and the difference between these two number was not significant. As a result, the classified accuracy of training samples were increasing while the training samples were increasing. By using the simulation testing method to compare the accuracy of learning rate, in any kind of mixed samples, when the learning rate was on 0.1, the classified accuracy was the worst; however the classified accuracy from other learning rates was irregular. When the number of hidden layers was 2, the classified accuracy was the best in any kind of mixed samples.

並列關鍵字

Neural Network ； Learning Vector Quantization ； Truncated Normal Distribution

參考文獻

吳致遠(1999)。類神經集群模式於企業債信評等之應用(碩士論文)。私立元智大學資訊研究所資訊管理組。

林素雲(1999)。利用類神經網路建構物件導向量測雛型研究－以光電元件(TFT-LCD)電測製程爲例(碩士論文)。國立交通大學資訊管理研究所。

梅永人(2000)。國語聲調電腦評量模式之研究(碩士論文)。國立台中師範學院教育測驗統計研究所。

葉怡成(1997)。應用類神經網路。台北市:儒林。

葉怡成(1997)。類神經網路模式應用與實作。台北市:儒林。