A Recurrent Latent Variable Model for Sequential Data
Annual Conference on Neural Information Processing Systems, 2015.
In this paper, we explore the inclusion of latent random variables into the hidden state of a recurrent neural network (RNN) by combining the elements of the variational autoencoder. We argue that through the use of high-level latent random variables, the variational RNN (VRNN)1 can model the kind of variability observed in highly structu...More
PPT (Upload PPT)