基于非线性预测的逆传播神经网络算法优化策略研究  

Study of optimization strategy for back propagation learning algorithm based on non-linear prediction method

作　　者：丛丽晖[1] 郑济仲[1] 李常山[1] 

机构地区：[1]沈阳航空工业学院计算机科学与工程系,辽宁沈阳110034

出　　处：《沈阳航空工业学院学报》2002年第4期32-34,共3页Journal of Shenyang Institute of Aeronautical Engineering

摘　　要：逆传播神经网络算法是人工神经网络用于非线性预测的主要学习算法 ,它具有思路清晰、结构严谨、可操作性强等特点 ,但同时也存在预测精度低、收敛速度慢等问题。本文从神经网络模型的结构出发 ,对学习算法提出了一系列改进和优化措施 ,以加快网络的学习速度 ,并增加模型的稳定性。The Back Propagation Learning Algorithm is the main learning algorithm applied artificial neural network to non-linear prediction, and has the characteristics of clear thinking, precise structure and strong maneuverability. But it also has some problems such as low prediction precision, slow convergence speed and so on. With the study of neural network model, this paper advances some of improvement and optimization techniques that can accelerate the learning speed of network and increase the stability of model.

关 键 词：非线性预测 优化 人工神经网络 逆传播学习算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]