Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
复制标题
DOI:
--
复制
发表时间:
2016-05
期刊:
影响因子:
--
通讯作者:
Maximilian Karl;Maximilian Sölch;Justin Bayer;Patrick van der Smagt
中科院分区:
文献类型:
--
作者:
Maximilian Karl;Maximilian Sölch;Justin Bayer;Patrick van der Smagt
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.