| 基于遗传算法的Bayesian网结构学习研究 |
| |
| 引用本文： | 刘大有,王飞,卢奕南,薛万欣,王松昕.基于遗传算法的Bayesian网结构学习研究[J].计算机研究与发展,2001,38(8):916-922. |
| |
| 作者姓名： | 刘大有 王飞 卢奕南 薛万欣 王松昕 |
| |
| 作者单位： | 吉林大学计算机科学系 |
| |
| 基金项目： | 国家“八六三”高技术研究发展计划 (86 3 -3 0 6 -ZD0 5 -0 1-2 )，国家自然科学基金 (6 9883 0 0 3 )，教育部高校博士点专项科研基 |
| |
| 摘 要： | 从不完备数据中学习网络结构是Bayesian网学习的难点之一，计算复杂度高，实现困难。针对该问题提出了一种进化算法。设计了结合数学期望的适应度函数，该函数利用进化过程中的最好Bayesian网把不完备数据转换成完备数据，从而大大简化了学习的复杂度，并保证算法能够向好的结构不断进化。此外，给出了网络结构的编码方案，设计了相应的遗传算子，使得该算法能够收敛到全局最优的Bayesian网结构。模拟实验结果表明，该算法能有效地从不完备数据中学习。
|
| 关 键 词： | Bayesian网 学习 遗传算法 数据处理 人工智能 |
RESEARCH ON LEARNING BAYESIAN NETWORK STRUCTURE BASED ON GENETIC ALGORITHMS |
| |
| LIU Da You,WANG Fei,LU Yi Nan,XUE Wan Xin,and WANG Song Xin.RESEARCH ON LEARNING BAYESIAN NETWORK STRUCTURE BASED ON GENETIC ALGORITHMS[J].Journal of Computer Research and Development,2001,38(8):916-922. |
| |
| Authors: | LIU Da You WANG Fei LU Yi Nan XUE Wan Xin and WANG Song Xin |
| |
| Abstract: | Learning structure from incomplete data is one of the difficulties of learning Bayesian networks because of computational complexity. In this paper, an evolutionary algorithm combined with expectation is proposed. Fitness function is presented, which based on expectation, converts incomplete data to complete data utilizing current best structure of evolutionary process to reduce computational complexity, ensuring that this algorithm can evolve for good structure. Besides, encoding is given, and genetic operators are designed, which provides guarantee of convergence. Experimental results show that this algorithm can effectively learn Bayesian network structure from incomplete data. |
| |
| Keywords: | learning Bayesian networks complete data incomplete data computational complexity genetic algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
