HackerPapers

arXiv:1506.02216cs.LG

A Recurrent Latent Variable Model for Sequential Data

Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron Courville, Yoshua Bengio

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

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.

arXiv comments
Journal reference
DOI
Subjects
cs.LGMachine Learning

On Hacker News

Linked by 1 identifiable commenter in 4 comments across 3 threads, from Jun 2015 to Aug 2015.

Comments linking this paper, per year.

Discussed in comments3 threads

  1. Classical music generation with recurrent neural networks 1 comment

    • This is really cool stuff - the network structure reminds me a lot of Graves' MDRNN[1] and Grid LSTM[2], as well as some work I helped with (ReNet [3]) I wonder if the structure over frequency/time is too "regular" - in general for sound the frequency correlation and the time…

      kastnerkyleView on HNParent context

  2. A Beginner’s Guide to Restricted Boltzmann Machines 1 comment

    • The literature is mostly image based, but as other users have said voice, text, and video have also seen substantial gains. It has also been used to great effect for taxi destination prediction (heterogenous information) [1], drug discovery [2], and general operations on graphs…

      kastnerkyleView on HNParent context

  3. Extending “Let It Go” with recurrent neural network 2 comments

    • If you are into this kind of stuff (time series density/probability modeling), there are several places to go beyond this. The simplest example is the RNN-RBM (restricted boltzmann machine) from the Theano deep learning tutorials [1]. There are follow-up papers by Kratarth Goel…

      kastnerkyleView on HNParent context

    • This is pretty hard - we use raw data for speech [1, talked about in comment above] but it still needs some work to do really good synthesis. FFT is not really the way to go either - then you still need to deal with the problems of complex data which is very, very unpleasant.…

      kastnerkyleView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.