Authors: Junyoung Chung , Kyle Kastner , Laurent Dinh , Kratarth Goel , Aaron C. Courville , Yoshua Bengio - Conference on Neural Information Processing Systems, NeurIPS 2015 cited by 1,378
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.
✨ Checking sign-in… PDF Cited by View BibTeX Hide BibTeX View BibTeX Cite
Long Short-Term Memory Long Short-Term Memory IAM-OnDB - an On-Line English Sentence… IAM-OnDB - an On-Line English Sentence Database Acquired from Handwritten Text on a Whiteboard Unsupervised feature learning for audio… Unsupervised feature learning for audio classification using convolutional deep belief networks Rectified Linear Units Improve Restricted… Rectified Linear Units Improve Restricted Boltzmann Machines Modeling Temporal Dependencies in… Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription Theano: new features and speed improvements Theano: new features and speed improvements LOL: An Investigation into Cybernetic Humor… LOL: An Investigation into Cybernetic Humor, or: Can Machines Laugh? Generating Sequences With Recurrent Neural… Generating Sequences With Recurrent Neural Networks Learning Stochastic Recurrent Networks Learning Stochastic Recurrent Networks Variational Recurrent Auto-Encoders Variational Recurrent Auto-Encoders Learning Phrase Representations using… Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation DRAW: A Recurrent Neural Network For Image… DRAW: A Recurrent Neural Network For Image Generation Black box variational inference for state… Black box variational inference for state space models Deep Temporal Sigmoid Belief Networks for… Deep Temporal Sigmoid Belief Networks for Sequence Modeling Social LSTM: Human Trajectory Prediction i… Social LSTM: Human Trajectory Prediction in Crowded Spaces Variational Neural Machine Translation Variational Neural Machine Translation Z-Forcing: Training Stochastic Recurrent… Z-Forcing: Training Stochastic Recurrent Networks Hierarchical Multiscale Recurrent Neural… Hierarchical Multiscale Recurrent Neural Networks A Disentangled Recognition and… A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning Generative Temporal Models with Memory Generative Temporal Models with Memory Stochastic WaveNet: A Generative Latent… Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data Noisin: Unbiased Regularization for… Noisin: Unbiased Regularization for Recurrent Neural Networks Stochastic Video Generation with a… Stochastic Video Generation with a Learned Prior Stochastic Latent Residual Video… Stochastic Latent Residual Video Prediction A Recurrent Latent Variable Model for… A Recurrent Latent Variable Model for Sequential Data Earlier references Focus paper Citing papers Older Newer Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.
