介電材料資料庫

A database that regulates the effects of side chain carbon number, benzene ring number, molecular weight, humidity, and testing frequency on the dielectric constant and dielectric loss when adding different polymers.(調控側鏈碳數、苯環數、分子量、溼度和測試頻率對添加不同高分子的介電常數和介電損失影響的資料庫)

The database is established by data mining and machine learning through the strategy of combining artificial neural networks with genetic algorithms. The learning procedure is 100,000 times, the root mean square (RMS) error is less than 0.002, and the error rate is less than 0.01.

資料庫中的數據是以資料探勘和機器學習方式，經結合基因演算與人工神經網絡的深度學習所建立。學習程序為100,000次，均方根（RMS）誤差小於0.002，誤率則小於0.01。