A Recurrent Latent Variable Model for Sequential Data Article Swipe

PDF

Related Concepts

Autoencoder Latent variable Recurrent neural network Computer science Artificial intelligence Latent variable model Hidden variable theory State variable State (computer science) Machine learning Artificial neural network Speech recognition Algorithm Quantum mechanics Physics Thermodynamics Quantum

Jun‐Young Chung , Kyle Kastner , Laurent Dinh , Kratarth Goel , Aaron Courville , Yoshua Bengio ·

YOU? · · 2015 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1506.02216 · OA: W592244745

In this paper, we explore the inclusion of latent random variables into the dynamic hidden state of a recurrent neural network (RNN) by combining 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 structured sequential data such as natural speech. We empirically evaluate the proposed model against related sequential models on four speech datasets and one handwriting dataset. Our results show the important roles that latent random variables can play in the RNN dynamic hidden state.