本文运用卡尔曼滤波原理,提出了一种新的神经网络学习算法。该算法的学习速度是由带时间参数的里卡蒂微分方程来确定的。
In this paper, making use of Kalman filtering, we derive a new back-propagation algorithm whose learning rate is computed by Riccati difference equation.
本文运用卡尔曼滤波原理,提出了一种新的神经网络学习算法。该算法的学习速度是由带时间参数的里卡蒂微分方程来确定的。
In this paper, making use of Kalman filtering, we derive a new back-propagation algorithm whose learning rate is computed by Riccati difference equation.
应用推荐