Note on Equivalence Between Recurrent Neural Network Time Series Models and Variational Bayesian Models
Machine Learning
2016-06-21 v2
Abstract
We observe that the standard log likelihood training objective for a Recurrent Neural Network (RNN) model of time series data is equivalent to a variational Bayesian training objective, given the proper choice of generative and inference models. This perspective may motivate extensions to both RNNs and variational Bayesian models. We propose one such extension, where multiple particles are used for the hidden state of an RNN, allowing a natural representation of uncertainty or multimodality.
Cite
@article{arxiv.1504.08025,
title = {Note on Equivalence Between Recurrent Neural Network Time Series Models and Variational Bayesian Models},
author = {Jascha Sohl-Dickstein and Diederik P. Kingma},
journal= {arXiv preprint arXiv:1504.08025},
year = {2016}
}