A structure and training algorithm for quasi-diagonal recurrent neural network (QDRNN) is presented.
提出一种准对角递归神经网络(QDRNN)结构及学习算法。
This provides a new way to the fast training of complex valued recurrent neural network.
这为快速训练复值递归神经网络提供了一条新的途径。
An adaptive gradient descent algorithm for training simplified internally recurrent networks (SIRN) is developed and a new method of reconciling nonlinear dynamic data based on SIRN is proposed.
研究了简化型内回归神经网络基于自适应梯度下降法的训练算法，并提出了一种基于简化型内回归神经网络的非线性动态数据校核新方法。
A new recurrent neural network based on B-spline function approximation is presented. The network can be easily trained and its training converges more quickly.
提出一种新的基于基本样条逼近的循环神经网络，该网络易于训练且收敛速度快。
A new training approach for the training algorithm of a fully connected recurrent neural network based on the digital filter theory is proposed.
一种新的基于数字滤波器理论的全互连复值递归神经网络训练方法被提出。
A new training approach for the training algorithm of a fully connected recurrent neural network based on the digital filter theory is proposed.
一种新的基于数字滤波器理论的全互连复值递归神经网络训练方法被提出。
应用推荐