| 示例学习算法IBLE和ID3的比较研究 |
| |
| 引用本文： | 钟鸣,陈文伟.示例学习算法IBLE和ID3的比较研究[J].计算机研究与发展,1993,30(1):32-38,8. |
| |
| 作者姓名： | 钟鸣 陈文伟 |
| |
| 作者单位： | 解放军防化研究院计算中心，解放军防化研究院计算中心，国防科学技术大学系统工程与数学系 北京，102205，北京，102205，长沙，410073 |
| |
| 摘 要： | 为了比较研究IBLE算法和ID_3算法的学习性能,本文用大量的质谱数据对两种算法做了学习实验。经过学习,IBLE 的平均预测率为93.96%。而ID_3为81.76%,而且IBLE 获得的知识在表示和内容上与专家知识具有较高一致性。文中对两种算法出现上述差异的原因进行了理论分析。
|
| 关 键 词： | 示例学习 ID3 IBLE 算法 质谱 |
Comparative Study of IBLE and ID_3 Algorithms for Learning From Examples |
| |
| Zhong Ming Liu Xiaoxia Computing Centre of Chemical Defence Institute,Beijing,
Chen Wenwei National University of Defence Technology,Changsha.Comparative Study of IBLE and ID_3 Algorithms for Learning From Examples[J].Journal of Computer Research and Development,1993,30(1):32-38,8. |
| |
| Authors: | Zhong Ming Liu Xiaoxia Computing Centre of Chemical Defence Institute Beijing Chen Wenwei National University of Defence Technology Changsha |
| |
| Affiliation: | Zhong Ming Liu Xiaoxia Computing Centre of Chemical Defence Institute,Beijing,102205
Chen Wenwei National University of Defence Technology,Changsha,410073 |
| |
| Abstract: | The learning performance of IBLE and ID_3 algorithms is compared and studied with
a great number of mass spectra.The average predictive accuracy is 93.96% for IBLE and 81.76% for
ID_3.The knowledge obtained by IBLE is quite identical with expert knowledge in the representation
and contents.The reason for the above differences between IBLE and ID_3 is discussed in theory. |
| |
| Keywords: | learning from examples knowledge acquisition ID_3 algorithm IBLE algorithm mass spectra |
| 本文献已被 CNKI 维普 等数据库收录！ |
