Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data

Understand

We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models.

• Leveraging recent advances in Stochastic Gradient Variational Bayes, DVBF can overcome intractable inference distributions via variational inference.
• Thus, it can handle highly nonlinear input data with temporal and spatial dependencies such as image sequences without domain knowledge.
• Our experiments show that enabling backpropagation through transitions enforces state space assumptions and significantly improves information content of the latent embedding.