Modelling long-term dependencies is a challenge for recurrent neural networks. This is primarily due to the fact that gradients vanish during training,... Read More

We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks. Whereas previous works only apply... Read More

We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states’ norms. This penalty term... Read More

In this paper, we explore the inclusion of random variables into the dynamic hidden state of a recurrent neural network (RNN) by... Read More