Improving mixing rate with tempered transition for learning restricted Boltzmann machines
Authors:
- Jungang XuJXJungang Xu
- Hui LiHLHui Li
- Shilong ZhouSZShilong Zhou
- 1 September 2014
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 139, 328-335
Abstract
No abstract availableThis publication has 20 references indexed in Scilit:
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Acoustic Modeling Using Deep Belief NetworksIEEE Transactions on Audio, Speech, and Language Processing, 2011
- On the Expressive Power of Deep Architectures2011
- Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines2010
- Semantic hashingInternational Journal of Approximate Reasoning, 2009
- Representational Power of Restricted Boltzmann Machines and Deep Belief NetworksNeural Computation, 2008
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- Sampling from multimodal distributions using tempered transitionsStatistics and Computing, 1996