改进的神经网络并行算法及其在地震初至拾取中的应用
|
摘要
针对经典BP神经网络易于陷入局部极小点、易于产生振荡等缺点,提出了神经网络初始权值的二分法,改进了一种网络结构自动确定算法,并将随机算子和遗忘因子引入BP神经网络中。在提高全局寻优能力的同时,加快了网络的收敛速度。在分析了神经网络内在并行性的基础上,基于MPI实现了改进算法的并行化,将算法应用于地震资料的初至拾取,并取得了良好的应用效果,验证了算法的有效性。
Based on analyzing the shortcoming of BP neural network,some methods are developed to improve the classic BP neural network,including the dichotomy to determine initialization of weights,an improved auto-determination method of network structure,random operator and forgetting factor introduced to BP neural network.With all these methods,the stronger capability of global optimization and quicker network's convergence speed have been obtained.Then after analyzing the internal parallel characteristic of neural network,the authors design and realize the parallel arithmetic of the improved BP neural network based on the MPI.The result of application in picking seismic first break is satisfactory and shows that the parallel arithmetic is effective.
Based on analyzing the shortcoming of BP neural network,some methods are developed to improve the classic BP neural network,including the dichotomy to determine initialization of weights,an improved auto-determination method of network structure,random operator and forgetting factor introduced to BP neural network.With all these methods,the stronger capability of global optimization and quicker network's convergence speed have been obtained.Then after analyzing the internal parallel characteristic of neural network,the authors design and realize the parallel arithmetic of the improved BP neural network based on the MPI.The result of application in picking seismic first break is satisfactory and shows that the parallel arithmetic is effective.
引文
[1]罗省贤,何大可.基于MPI的网络并行计算环境及应用[M].成都:西南交通大学出版社,2001.
[2]刘耦耕,贺素良.BP神经网络结构参数的计算机自动确定[J].计算机工程与应用,2004,13:72-75.
[3]LI Jun,LI Yuan-xiang,XUJing-wen,et al.Paralleltraining algorithmof BP neural networks[C]//Intel-ligent Control and Automation,2000.Processings ofthe 3rdWorld Congress on 2000,2000,(2):872-876.
[4]YAMAMORI K,ABE T,HORIGUCHI S.Two-stage parallel partial retraining scheme for defectivemulti-layer neural networks[C]//High PerformanceComputing in the Asia-Pacific Region,2000.Pro-ceedings.The Fourth International Conference/Exhi-bition on,2000,2:642-647.
[5]胡月,熊忠阳.一种新的BP算法并行策略[J].计算机工程,2005,31(8):148-150.
[2]刘耦耕,贺素良.BP神经网络结构参数的计算机自动确定[J].计算机工程与应用,2004,13:72-75.
[3]LI Jun,LI Yuan-xiang,XUJing-wen,et al.Paralleltraining algorithmof BP neural networks[C]//Intel-ligent Control and Automation,2000.Processings ofthe 3rdWorld Congress on 2000,2000,(2):872-876.
[4]YAMAMORI K,ABE T,HORIGUCHI S.Two-stage parallel partial retraining scheme for defectivemulti-layer neural networks[C]//High PerformanceComputing in the Asia-Pacific Region,2000.Pro-ceedings.The Fourth International Conference/Exhi-bition on,2000,2:642-647.
[5]胡月,熊忠阳.一种新的BP算法并行策略[J].计算机工程,2005,31(8):148-150.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心