Approximation properties of DBNs with binary hidden units and real-valued visible units
By Oswin Krause, Asja Fischer, Tobias Glasmachers, Christian Igel. 2013
10 citations recorded by the source corpus.
Subfields: Representation & Self-Supervised Learning, Probabilistic & Bayesian Methods
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Representation & Self-Supervised Learning
- Kyunghyun Cho
- Asja Fischer
- Razvan Pascanu
- Christian Igel
- Guido Montúfar
- Yoshua Bengio
- Pascal Vincent
- Li Deng
In Probabilistic & Bayesian Methods
- Asja Fischer
- Kyunghyun Cho
- Christian Igel
- Yoshua Bengio
- Guido Montúfar
- Razvan Pascanu
- Pascal Vincent
- L. Yao
Citations in the corpus
- On the Number of Linear Regions of Deep Neural Networks (2014, background): “Other works have investigated universal approximation of probability distributions by deep belief networks (Le Roux and Bengio 2010, Mont´ufar and Ay 2011), as well as their approximation properties (Mont´ufar 2014, Krause et al. 2013).”
- Training restricted Boltzmann machines: An introduction (2014, background): “However, if we add an additional layer of binary latent variables, we can model any strictly positive density over a compact domain with arbitrary high accuracy [30].”
- Training Restricted Boltzmann Machines (2015, methodology): “Therefore, we analyze [13] the approximation properties of DBNs with two layers of binary hidden units, and visible units with conditional distributions from the exponential family.”