摘要
针对现有的利用非线性滤波算法对神经网络进行训练中存在滤波精度受限和效率不高的缺陷,提出一种基于容积卡尔曼滤波(CKF)的神经网络训练算法.在算法实现过程中,首先构建神经网络的状态空间模型;然后将网络连接权值作为系统的状态参量,并采用三阶Spherical-Radial准则生成的容积点实现神经网络中节点连接权值的训练.理论分析和仿真结果验证了所提出算法的可行性和有效性.
Aiming at the defects of filtering precision limitation and low efficiency in using the existing nonlinear filtering algorithms for neural network training, a novel neural network training algorithm based on the cubature Kalman filter is proposed. Firstly, the state space model of the neural network is established. Then the network connection weights are used as the state of the system’s parameters, and the training process of neural network weights is realized by a set of cubature points produced by adopting the third-order spherical-radial standards. The theoretical analysis and simulation results show the feasibility and effectiveness of the proposed algorithm.
出处
《控制与决策》
EI
CSCD
北大核心
2016年第2期355-360,共6页
Control and Decision
基金
国家自然科学基金项目(61300214)
中国博士后科学基金项目(2014M551999)
河南省高校科技创新团队支持计划项目(13IRTSTHN021)
河南省博士后科学基金项目(2013029)
河南省高校青年骨干教师计划项目(2013GGJS-026)
河南大学优秀青年培育基金项目(0000A40366)
关键词
非线性滤波
容积卡尔曼滤波
神经网络
多层感知器
nonlinear filter
cubature Kalman filter
neural network
multi-layer perceptions