【摘要】 为解决现有的BP神经网络对私家车保有量的预测中存在的对初始权值和阈值敏感、易陷入局部极小点和收敛速度慢等问题,针对粒子群算法具有全局搜索寻优的特点,该文提出了基于熵值法的采用粒子群算法优化的BP神经网络的模型。我们用新建立的模型进行私家车保有量的预测,并将其结果与传统BP算法以及模拟退火法进行比较,结果表明新的模型有效的防止了网络陷入局部极小值的可能,明显提高了神经网络模型预测的速度和准确性。更多还原

【Abstract】 In order to solve the existing problems such as the initial weights and threshold-sensitive,easily falling into local minima and slow convergence in the total number prediction of private cars by using BP neural network,this paper proposes the use of entropy-based particle swarm optimization algorithm BP neural network model.And we will use the model to predict the amount of private cars study and compare its results with the traditional BP algorithm and simulated annealing method.The results show that the new model is effective to prevent the network may fall into local minima and significantly improve the speed and accuracy of neural network model.更多还原