论文部分内容阅读
将卡尔曼滤波算法引入到递归神经网络的训练当中,并针对递归神经网络、卡尔曼算法及BP算法的特点,提出了用于递归神经网络的分层学习算法,并给出了理论分析.仿真结果证明了本算法的有效性.
The Kalman filter algorithm is introduced into the training of recurrent neural network. According to the characteristics of recurrent neural network, Kalman algorithm and BP algorithm, a hierarchical learning algorithm for recurrent neural network is proposed and a theoretical analysis is given. Simulation results show the effectiveness of the proposed algorithm.