基于迭代容积卡尔曼滤波的神经网络训练算法

Novel Neural Network Training Algorithm Based on Iterated Cubature Kalman Filter

针对现有应用非线性滤波算法对神经网络进行训练时存在精度不足的问题,提出了一种基于迭代容积卡尔曼滤波的神经网络训练算法。首先,将前馈神经网络各个节点的连接权值和偏置作为状态向量,建立前馈神经网络的状态空间模型。其次,利用Spherical-Radial准则生成容积点,并依据Gauss-Newton迭代策略来优化量测更新过程中获取的状态估计值和状态估计误差协方差,通过容积卡尔曼滤波估计精度的改善,提升神经网络节点的连接权值和偏置的训练效果。理论分析和仿真实验结果验证了所提算法的可行性和有效性。

In view of insufficient accuracy in the existing application of nonlinear filtering algorithm for neural network training,a novel neural network training algorithm based on iterated cubature Kalman filter was proposed. Firstly, the connection weights and bias of feedforward neural network are used as the state vector to establish the state space mo- del. Secondly, using the Spherical-Radial standard to generate cubature points, the state estimation and covariance ac- quired during the measurement update process are optimized based on Gauss-Newton iteration strategy. The training effect of neural network connecting weights and bias is enhanced through the improvement of the estimation precision of cubature Kalman filter. The theoretical analysis and simulation results show the feasibility and effectiveness of the algo- rithm.