A REAL-TIME LEARNING ALGORITHM FOR A MULTILAYERED NEURAL NETWORK BASED ON THE EXTENDED KALMAN FILTER
A REAL-TIME LEARNING ALGORITHM FOR A MULTILAYERED NEURAL NETWORK BASED ON THE EXTENDED KALMAN FILTER
复制标题
DOI：
10.1109/78.127966
复制
发表时间：
1992-04-01
影响因子：
5.4
通讯作者：
TOKUMARU, H
中科院分区：
文献类型：
--
作者：
IIGUNI, Y;SAKAI, H;TOKUMARU, H
扩展卡尔曼滤波器（EKF）作为非线性系统的状态估计方法是公知的，并且可以用作通过用未知参数扩充状态的参数估计方法。 多层神经网络是一种具有分层结构的非线性系统，其学习算法可看作是对这种非线性系统的参数估计，本文从扩展卡尔曼滤波（EKF）出发，导出了一种新的多层神经网络实时学习算法。 由于这种基于EKF的学习算法近似地给出了链路权值的最小方差估计，因此与使用最速下降技术的向后误差传播算法相比，收敛性能得到了改善。 此外，调整参数的关键控制收敛性能不包括在内，这使得它的应用更容易。 异或和奇偶校验问题的仿真结果。
The extended Kalman filter (EKF) is well known as a state estimation method for a nonlinear system, and can be used as a parameter estimation method by augmenting the state with unknown parameters. A multilayered neural network is a nonlinear system having a layered structure, and its learning algorithm is regarded as parameter estimation for such a nonlinear system.In this paper, a new real-time learning algorithm for a multilayered neural network is derived from the EKF. Since this EKF-based learning algorithm approximately gives the minimum variance estimate of the linkweights, the convergence performance is improved in comparison with the backwards error propagation algorithm using the steepest descent techniques. Furthermore, tuning parameters which crucially govern the convergence properties are not included, which makes its application easier. Simulation results for the XOR and parity problems are provided.