Learning Stochastic Recurrent Networks

Abstract

Leveraging advances in variational inference, we propose to enhance recurrent neural networks with latent variables, resulting in Stochastic Recurrent Networks (STORNs). The model i) can be trained with stochastic gradient methods, ii) allows structured and multi-modal conditionals at each time step, iii) features a reliable estimator of the marginal likelihood and iv) is a generalisation of deterministic recurrent neural networks. We evaluate the method on four polyphonic musical data sets and motion capture data.

Submitted to conference track of ICLR 2015

References in corpus (4)

• ADADELTA: An Adaptive Learning Rate Method
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
• Speech Recognition with Deep Recurrent Neural Networks

Cited by in corpus (30)

• TensorFlow Distributions
• Variational Recurrent Auto-Encoders
• Generative Temporal Models with Memory
• Z-Forcing: Training Stochastic Recurrent Networks
• State Space LSTM Models with Particle MCMC Inference
• Perpetual Motion: Generating Unbounded Human Motion
• Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
• Disentangled State Space Representations
• Social-VRNN: One-Shot Multi-modal Trajectory Prediction for Interacting Pedestrians
• State-Regularized Recurrent Neural Networks
• A Classifying Variational Autoencoder with Application to Polyphonic Music Generation
• Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection
• S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation
• Variational Bi-LSTMs
• A Latent Feelings-aware RNN Model for User Churn Prediction with Behavioral Data
• Variational Tracking and Prediction with Generative Disentangled State-Space Models
• Stochastic Sequential Neural Networks with Structured Inference
• Unsupervised Contextual Anomaly Detection using Joint Deep Variational Generative Models
• Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
• Relational State-Space Model for Stochastic Multi-Object Systems
• Human Pose Forecasting via Deep Markov Models
• Policy Gradients Incorporating the Future
• Regularized Sequential Latent Variable Models with Adversarial Neural Networks
• Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models
• Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations
• Hierarchical Variational Imitation Learning of Control Programs
• Introducing a Generative Adversarial Network Model for Lagrangian Trajectory Simulation
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder
• Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements
• A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling