Iterative Refinement of Approximate Posterior for Training Directed Belief Networks
By R. Devon Hjelm, Kyunghyun Cho, Junyoung Chung, Ruslan Salakhutdinov, Vince D. Calhoun, Nebojsa Jojic. 2015
7 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Asja Fischer
- David Kristjanson Duvenaud
- Xuechen Li
- Jörg Bornschein
- Ruslan Salakhutdinov
- Sergey Levine
- Arash Vahdat
Citations in the corpus
- Inference Suboptimality in Variational Autoencoders (2018, methodology): “More recent work has applied this idea to improve approximate inference in directed Belief networks (Hjelm et al., 2015).”
- Bidirectional Helmholtz Machines (2015, methodology): “In (Hjelm et al., 2015) the authors propose an iterative, gradient based procedure to refine the approximate posterior.”