论文标题
洗牌复发性神经网络
Shuffling Recurrent Neural Networks
论文作者
论文摘要
我们提出了一个新颖的经常性神经网络模型，其中隐藏状态$ h_t $是通过将先前隐藏状态的向量元素$ h_ {t-1} $获得的，并添加了$ x_t $ x_t $ time $ t $的输入$ b（x_t）$的输出。在我们的模型中，预测由第二个学习的功能给出，该功能应用于隐藏状态$ s（H_T）$。该方法易于实施，非常高效，并且不会因消失或爆炸梯度而受苦。在一组广泛的实验中，与主要文献基线相比，该方法显示出竞争性结果。
We propose a novel recurrent neural network model, where the hidden state $h_t$ is obtained by permuting the vector elements of the previous hidden state $h_{t-1}$ and adding the output of a learned function $b(x_t)$ of the input $x_t$ at time $t$. In our model, the prediction is given by a second learned function, which is applied to the hidden state $s(h_t)$. The method is easy to implement, extremely efficient, and does not suffer from vanishing nor exploding gradients. In an extensive set of experiments, the method shows competitive results, in comparison to the leading literature baselines.
