Unsupervised Neural Hidden Markov Models with a Continuous latent state space
Not on the map. Why?
Abstract (arXiv)
We introduce a new procedure to neuralize unsupervised Hidden Markov Models in the continuous case. This provides higher flexibility to solve problems with underlying latent variables. This approach is evaluated on both synthetic and real data. On top of generating likely model parameters with comparable performances to off-the-shelf neural architecture (LSTMs, GRUs,..), the obtained results are easily interpretable.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 25 references that are in the map. First posted on arXiv 10 Jun 2021.
Builds on
7 of 25 references.
References · 7
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2016Composing graphical models with neural networks for structured representations and fast inferencecited by 113
- 2014On Particle Methods for Parameter Estimation in State-Space Modelscited by 47
- 2016Unsupervised Neural Hidden Markov Modelscited by 19
- 2018Bayesian Reinforcement Learning in Factored POMDPscited by 15
- 2018Hierarchical Reinforcement Learning Framework towards Multi-agent Navigationcited by 7
- 2019Markov Decision Process for MOOC users behavioral inferencecited by 2
Built on by
Not cited yet.