摘要
Learning Bayesian network is an NP-hard problem. When the number of variables is large, the process of searching optimal network structure could be very time consuming and tends to return a structure which is local optimal.The particle swarm optimization (PSO) was introduced to the problem of learning Bayesian networks and a novel structure learning algorithm using PSO was proposed. To search in directed acyclic graphs spaces efficiently, a discrete PSO algorithm especially for structure learning was proposed based on the characteristics of Bayesian networks. The results of experiments show that our PSO based algorithm is fast for convergence and can obtain better structures compared with genetic algorithm based algorithms.
Learning Bayesian network is an NP-hard problem. When the number of variablesis large, the process of searching optimal network structure could be very time consuming and tendsto return a structure which is local optimal. The particle swarm optimization (PSO) was introducedto the problem of learning Bayesian networks and a novel structure learning algorithm using PSO wasproposed. To search in directed acyclic graphs spaces efficiently, a discrete PSO algorithmespecially for structure learning was proposed based on the characteristics of Bayesian networks.The results of experiments show that our PSO based algorithm is fast for convergence and can obtainbetter structures compared with genetic algorithm based algorithms.
基金
National Natural Science Foundation of Chi-na (No.60374071)
Zhenjiang Commissionof Science and Technology ( No.2003C11009)
