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

01 Mar 2021 (modified: 03 Mar 2017)ICLR 2017 conference submissionReaders: Everyone
  • Abstract: 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. This also enables realistic long-term prediction.
  • Keywords: Deep learning, Unsupervised Learning
  • Conflicts: tum.de, tu-darmstadt.de, iit.it, fortiss.org
12 Replies

Loading