Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference.
Erik NijkampBo PangTian HanLinqi ZhouSong-Chun ZhuYing Nian WuPublished in: ECCV (6) (2020)
Keyphrases
- multi layer
- approximate inference
- latent variable models
- latent variables
- graphical models
- neural nets
- learning algorithm
- belief propagation
- structured prediction
- message passing
- parameter estimation
- learning process
- probabilistic model
- reinforcement learning
- hidden markov models
- machine learning
- prior knowledge
- learning tasks
- bayesian networks
- gaussian process
- hidden variables
- feature selection