How can you use Dropout to handle missing inputs in recurrent neural network? A nice paper by my student Francesco Crecchi is going to answer this at IJCNN2017
DropIn: Making Neural Networks Robust to Missing Inputs by Dropout. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN 2017) , IEEE, 2017, ISBN: 978-1-5090-6182-2.