| 快速神经网络分类学习算法的研究及其应用 |
| |
| 引用本文： | 刘海涛,周志华,陆新泉,陈兆乾,郑仁辉. 快速神经网络分类学习算法的研究及其应用[J]. 计算机研究与发展, 2000, 37(11): 1306-1310 |
| |
| 作者姓名： | 刘海涛 周志华 陆新泉 陈兆乾 郑仁辉 |
| |
| 作者单位： | 1. 南京大学计算机软件新技术国家重点实验室,南京,210093
2. 北京地球软件技术开发公司,北京,100080 |
| |
| 基金项目： | 国家自然科学基金!(项目编号 6 9875 0 0 6 )，江苏省自然科学基金!(项目编号 BK990 36 ) |
| |
| 摘 要： | 提出了一种快速神经网络分类学习算法FTART2，该算法结合了自适应谐振理论和域理论的优点，学习速度快、归纳能力强、效率高，用UCI机器学习数据库中的两个数据集对FTART2与目前最流行的BP进行比较测试，实验结果表明前者的分类精度与学习速度均优于后者，还将FTART2算法应用于石油地质储层分析领域，取得了很好的效果。
|
| 关 键 词： | 神经网络 机器学习 模式识别 分类 学习算法 |
RESEARCH AND APPLICATION OF A FAST NEURAL CLASSIFICATION ALGORITHM |
| |
| LIU Hai-Tao,ZHOU Zhi-Hua,LU Xin-Quan,CHEN Zhao-Qian,ZHENG Ren-Hui. RESEARCH AND APPLICATION OF A FAST NEURAL CLASSIFICATION ALGORITHM[J]. Journal of Computer Research and Development, 2000, 37(11): 1306-1310 |
| |
| Authors: | LIU Hai-Tao ZHOU Zhi-Hua LU Xin-Quan CHEN Zhao-Qian ZHENG Ren-Hui |
| |
| Abstract: | A fast neural classification algorithm named FTART2 is proposed in this paper. It combines the advantages of both adaptive resonance theory and field theory resulting in fast learning speed, strong generality, and high efficiency. FTART2 is tested against the most prevailing neural algorithm BP using two data sets from UCI machine learning repository. Experimental results show that the former is better than the latter in both classification accuracy and learning speed. Moreover, FTART2 has also been applied to the analysis of oil reservoir and satisfactory results have been achieved. |
| |
| Keywords: | neural networks machine learning pattern recognition classification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
