# Unsupervised Neural Hidden Markov Models with a Continuous latent state space

arXiv: https://arxiv.org/abs/2106.06536 · HTML: https://mlsanity.com/paper/2106.06536/

## 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 (most cited first, 7 of 7)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Composing graphical models with neural networks for structured representations and fast inference](https://mlsanity.com/paper/1603.06277/) (2016)
- [On Particle Methods for Parameter Estimation in State-Space Models](https://mlsanity.com/paper/1412.8695/) (2014)
- [Unsupervised Neural Hidden Markov Models](https://mlsanity.com/paper/1609.09007/) (2016)
- [Bayesian Reinforcement Learning in Factored POMDPs](https://mlsanity.com/paper/1811.05612/) (2018)
- [Hierarchical Reinforcement Learning Framework towards Multi-agent Navigation](https://mlsanity.com/paper/1807.05424/) (2018)
- [Markov Decision Process for MOOC users behavioral inference](https://mlsanity.com/paper/1907.04723/) (2019)

## 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.