演化神经网络学习方法及其应用
|
摘要
在基于梯度下降原理的ＢＰ网络学习过程中，权值的获取方法是采用某个确定的权值变化规则，然后在训练中逐步调整，最终得到一个较好的权值分布。但它往往会因非线性多极值目标函数而陷于局部最优解。本文采用全局寻优的遗传算法（ＧＡ）和基于梯度下降的局部寻优反传算法（ＢＰ）相结合来训练网络，使网络的连接权在不断迭代过程中自适应演化。通过在ＮＨ地区利用井旁道地震特征参数外推重建井底以下声波曲线的实践，表明这种演化学习方法可以克服传统方法的不足，而且还能避免训练中的“伪学习”现象，提高网络的推广预测能力。
During the learning process of back-propagation (BP) networks based on gradient descent principle, a good weighting value distribution can be finally obtained from adopting certain definite rule of weights variation and then gradually adjusting it in training in ordinary method, but it usually falls into local optimal solution because of nonlinear multi-extreme object function. Training networks combining genetic algorithm (GA ) based on global optimization with backpropagation (BP) based on gradient descent in the paper make the linking weights of networks self-adaptive evolution in constantly iterative process. The practice reconstructing sonic logging under bottom hole in NH area by extrapolating seismic characteristic parameters of near-well bore traces shows that the evolutionary learning method can overcome shortcomings of traditional method, and avoid “pseudo-learning”phenomenon in the training and improve popularizing and predicting ability for networks.
During the learning process of back-propagation (BP) networks based on gradient descent principle, a good weighting value distribution can be finally obtained from adopting certain definite rule of weights variation and then gradually adjusting it in training in ordinary method, but it usually falls into local optimal solution because of nonlinear multi-extreme object function. Training networks combining genetic algorithm (GA ) based on global optimization with backpropagation (BP) based on gradient descent in the paper make the linking weights of networks self-adaptive evolution in constantly iterative process. The practice reconstructing sonic logging under bottom hole in NH area by extrapolating seismic characteristic parameters of near-well bore traces shows that the evolutionary learning method can overcome shortcomings of traditional method, and avoid “pseudo-learning”phenomenon in the training and improve popularizing and predicting ability for networks.
引文
1肖慈,娄建立,谭世君.神经网络技术用于测井解释的评述.测井技术,1999,23(5):389～392
2潘正君,康立山,陈毓屏.演化计算,清华大学出版社,1998
3陈国良,王煦法,庄正泉,王东升.遗传算法及其应用,人民邮电出版社,1996
4刘勇,康立山,陈毓屏.非数字并行算法(二)──遗传算法,科学出版社,1995
5周明,孙树栋.遗传算法原理及应用,国防工业出版社,1999
6彭真明,韩燕君.遗传算法及其在剩余静校正中的应用.断块油气田,1998,5(1):5～8
7 Yao X.A Review of evolutionary artificial neural networks. International Journal of Intelligent Sys- tems,1993, 8(4)
2潘正君,康立山,陈毓屏.演化计算,清华大学出版社,1998
3陈国良,王煦法,庄正泉,王东升.遗传算法及其应用,人民邮电出版社,1996
4刘勇,康立山,陈毓屏.非数字并行算法(二)──遗传算法,科学出版社,1995
5周明,孙树栋.遗传算法原理及应用,国防工业出版社,1999
6彭真明,韩燕君.遗传算法及其在剩余静校正中的应用.断块油气田,1998,5(1):5～8
7 Yao X.A Review of evolutionary artificial neural networks. International Journal of Intelligent Sys- tems,1993, 8(4)
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