摘要
贝叶斯网络源于人们对人工智能领域不确定性问题的研究,是进行不确定问题推理和数据分析的重要工具。结构学习是贝叶斯网络研究的核心内容,K2算法是结构学习的经典算法之一。为解决K2算法学习效果强烈依赖于节点序的问题,提出一种新的混合结构学习算法:双重K2算法。首先将节点信息作为初始节点序,通过K2算法的搜索策略得到初始网络结构;然后在初始网络结构上利用拓扑排序得到修正后的节点序;最后K2算法通过修正后的节点序学习得到最优的网络结构。实验结果表明:在精度和效率上,双重K2算法效果优于其他经典算法。
Bayesian network originates from people’s research on uncertainty problems in the field of artificial intelligence, and it is an important tool for uncertainty problems inference and data analysis. Structure learning is the core content of Bayesian network research, and the K2 algorithm is one of the classical algorithms for structure learning. In order to solve the problem that the learning effect of K2 algorithm strongly depends on the node order, a new hybrid structure learning algorithm: double K2 algorithm was proposed. Firstly, the node information was taken as the initial node order, and the initial network structure was obtained through the search strategy of K2 algorithm. Then, the modified node order was obtained by using topological ordering on the initial network structure. Finally, K2 algorithm was obtained the optimal network structure through the modified node order. Experimental results show that the double K2 algorithm is better than other classical algorithms in accuracy and efficiency.
作者
李晓晴
于海征
LI Xiao-qing;YU Hai-zheng(Mathematics and Systems Science College,Xinjiang University,Urumqi 830046,China)
出处
《科学技术与工程》
北大核心
2022年第24期10602-10610,共9页
Science Technology and Engineering
基金
国家自然科学基金(61662079,11761070,U1703262)
新疆维吾尔自治区自然科学基金面上项目(2021D01C078)。
关键词
贝叶斯网络
结构学习
节点序
K2算法
Bayesian network
structural learning
the node order
K2 algorithm
