Object Class Segmentation of RGB-D Video using Recurrent Convolutional Neural Networks Mircea Serban Pavel

关于深度学习神经网络参数更新方法的文献

关于深度学习神经网络参数更新方法的文献

A finite-time recurrent neural network for solving online time-varying Sylvester matrix equation based on a new evolution formula

A one-layer recurrent neural network for constrained nonsmooth invex optimization

recurrent batch normalization的pytorch实现

GRU（Gated Recurrent Unit）神经网络是LSTM 的一个变体，GRU 在保持了LSTM 的效果同时又使结构更加简单，是一种非常流行RNN 神经网络，它只有两个门了，分别为更新门t z 和重置门tr 。更新门控制前一时刻的状态信息被带入到当前状态中的程度，值越大前一时刻的状态信息带入越多。重置门控制忽略前一时刻的状态信息的程度，值越小说明忽略得越多。

recurrent neural network without a phd.pdf 出处：https://github.com/martin-gorner/tensorflow-rnn-shakespeare

Recurrent Neural Networks for Prediction offers a new insight into the learning algorithms, architectures and stability of recurrent neural networks and, consequently, will have instant appeal. It provides an extensive background for researchers, academics and postgraduates enabling them to apply such networks in new applications.