标准粒子群算法易陷入局部最优值。
Standard particle swarm algorithm is easy to fall into local optimum.
改进后的遗传算法通过二次演化能够有效地避免算法中容易陷入局部最优值的缺陷。
Improved Genetic Algorithms can avoid the defect of reaching the part best value easily by the twice evolution.
实验结果证明,优化后的BP网络可有效地避免收敛于局部最优值,大大地缩短了训练时间。
The results show the optimized BP neural network can effectively avoid converging on local optimum and reduce training time greatly.
应用推荐