http://scholars.ntou.edu.tw/handle/123456789/22537
標題: | Exploring the factor effect of learning vector quantization in artificial neural networks | 作者: | Yih Shan Shih Liang-Ting Tsai Chih Chien Yang |
關鍵字: | ANNs;Artificial Neural Network (ANN);Effect Factor;Learning Vector Quantization;LVQ | 公開日期: | 一月-2013 | 卷: | 284-287 | 起(迄)頁: | 3097-3101 | 來源出版物: | Applied Mechanics and Materials | 摘要: | The goal of this study is to explore the factor effect of learning vector quantization. The manipulated factors are training pattern, learning rate, types of mixed data, and hidden node. The results showed that the average accuracy for severe overlap data was significantly lower than for those of slight and moderate overlap data. The worst classification accuracy was found for mixed data with learning rate equals to 0.1; whereas the best classification accuracy was found when the number of hidden nodes and output categories are equal. As a result, the classification accuracy increased as the number of training patterns increased. Conclusions and discussions are provided for practical guidelines. |
URI: | http://scholars.ntou.edu.tw/handle/123456789/22537 | ISSN: | 1662-7482 | DOI: | https://doi.org/10.4028/www.scientific.net/AMM.284-287.3097 |
顯示於: | 教育研究所 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。