mlsanityData to 7 Oct 2026

Sequential Neural Models with Stochastic Layers

arXiv 1605.07571 ↗First posted 24 May 2016stat.ML cs.LGcited by 115

Not on the map. Why?

Abstract (arXiv)

How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model. The clear separation of deterministic and stochastic layers allows a structured variational inference network to track the factorization of the model's posterior distribution. By retaining both the nonlinear recursive structure of a recurrent neural network and averaging over the uncertainty in a latent path, like a state space model, we improve the state of the art results on the Blizzard and TIMIT speech modeling data sets by a large margin, while achieving comparable performances to competing methods on polyphonic music modeling.

Key facts. Cited by 115 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 2; 2020: 0; 2021: 29; 2022: 26; 2023: 20; 2024: 14; 2025: 9; 2026: 15.

115 papers.

Sort:

By area:

  1. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 258
  2. 2024Deep Time Series Models: A Comprehensive Survey and Benchmarkcited by 191
  3. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 101
  4. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  5. 2021RAVE: A variational autoencoder for fast and high-quality neural audio synthesiscited by 72
  6. 2022SocialVAE: Human Trajectory Prediction using Timewise Latentscited by 65
  7. 2021Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modelingcited by 59
  8. 2022Criteria for Classifying Forecasting Methodscited by 48
  9. 2023Causal Recurrent Variational Autoencoder for Medical Time Series Generationcited by 44
  10. 2021Noisy Recurrent Neural Networkscited by 42
  11. 2021Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encodercited by 39
  12. 2023Deep networks for system identification: a Surveycited by 35
38 more
  1. 2022Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systemscited by 34
  2. 2023Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecastingcited by 33
  3. 2021Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecastingcited by 29
  4. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
  5. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  6. 2021Model-Based Reinforcement Learning via Latent-Space Collocationcited by 27
  7. 2021Bayesian Attention Belief Networkscited by 25
  8. 2019Learning Belief Representations for Imitation Learning in POMDPscited by 23
  9. 2024CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Processcited by 20
  10. 2021Online Variational Filtering and Parameter Learningcited by 19
  11. 2022Evaluation of creating scoring opportunities for teammates in soccer via trajectory predictioncited by 19
  12. 2021CAMul: Calibrated and Accurate Multi-view Time-Series Forecastingcited by 17
  13. 2022Data-to-text Generation with Variational Sequential Planningcited by 17
  14. 2024MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videoscited by 17
  15. 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecastingcited by 16
  16. 2022HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAEcited by 16
  17. 2026Generative Recursive Reasoningcited by 16
  18. 2021Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Modelscited by 14
  19. 2022Conditional Generation of Medical Time Series for Extrapolation to Underrepresented Populationscited by 14
  20. 2022Predicting the Next Action by Modeling the Abstract Goalcited by 14
  21. 2022Latent State Marginalization as a Low-cost Approach for Improving Explorationcited by 13
  22. 2021Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modelingcited by 11
  23. 2022Estimating counterfactual treatment outcomes over time in complex multiagent scenarioscited by 11
  24. 2021A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Predictioncited by 10
  25. 2022A Brief Overview of Unsupervised Neural Speech Representation Learningcited by 9
  26. 2021GATSBI: Generative Agent-centric Spatio-temporal Object Interactioncited by 8
  27. 2022Low-Rank Constraints for Fast Inference in Structured Modelscited by 8
  28. 2023A generative model for surrogates of spatial-temporal wildfire nowcastingcited by 8
  29. 2025BRAID: Input-Driven Nonlinear Dynamical Modeling of Neural-Behavioral Datacited by 8
  30. 2026Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Trackingcited by 7
  31. 2021VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Expertscited by 6
  32. 2022Probabilistic Decomposition Transformer for Time Series Forecastingcited by 6
  33. 2023Time-Transformer: Integrating Local and Global Features for Better Time Series Generation (Extended Version)cited by 6
  34. 2023Continuous-time Autoencoders for Regular and Irregular Time Series Imputationcited by 6
  35. 2019Hierarchical Variational Imitation Learning of Control Programscited by 5
  36. 2022Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learningcited by 5
  37. 2023Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systemscited by 5
  38. 2024Deep Bayesian Filter for Bayes-faithful Data Assimilationcited by 5

50 most cited of 115 All 115 (JSON)