摘要： 针对BP神经元网络训练过程中收敛速度缓慢,易陷入局部极值的缺点,提出了通过划分权值空间寻找最小极值区域,在此基础上并行化BP算法的二次并行搜索策略,并将此策略应用于医药物流系统的销售趋势预测。实验证明该算法能快速找到全局最小,并在大样本集的情况下,训练速度有显著提高。

关键词: 人工神经网络, BP算法, 并行训练, PVM

Abstract: A solution named two times parallel search strategy based on back propagation algorithm is proposed to cover the disadvantages of slow convergence and frequent local vibration. The experiment results show that the strategy reaches global minimum soon and converges at high rate, especially to a large training samples.

中图分类号: 

• TP183