欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
提出一种基于粒子群算法优化BP网络的权值调整新方法．该算法在基本BP算法的误差反传调整权值的基础上，再引入粒子群算法的权值修正，从而建立了基于粒子群算法优化的BP网络新模型．此模型不仅可以克服基本BP算法收敛速度慢和易陷入局部极值的局限，而且模型的精度较高，较好地提高了BP网络学习能力与泛化能力．将新模型应用于4个典型复杂函数的仿真实验，并与基本BP模型、基于遗传算法优化的BP网络模型（GA-BP）和传统的粒子群优化前向BP网络模型（PSO-BP前传）的仿真实验结果进行分析比较．仿真实例表明新PSO-BP优化模型性能尤其是泛化性能优于其它3种BP网络优化模型．
英文摘要：
A new method to adjust weights of BP network was proposed based on particle swarm optimization. The new model was based on the weight adjustments of error back propagation of BP algorithm and the weight modification using particle swarm optimization （PSO）. The model can not only overcome the limitations both the slow convergence and the local extreme values by basic BP algorithm, but also improve the learning ability and generalization ability with a higher precision. The new model was used in simulation test of four typical complex functions, results of which were analysed and compared with that of basic BP algorithm, BP network optimized based on genetic algorithm （GA-BP） and traditional BP network of signal forward propagation based on particle swarm optimization.Results show the performances of new PSO-BP model are superior to that of other 3 kinds of optimized BP network models, especially in generalization ability.
同期刊论文项目
同项目期刊论文
期刊信息
位置：