Continuous Sigmoidal Belief Networks Trained Using Slice Sampling
Abstract
Real-valued random hidden variables can be useful for modelling latent structure that explains correlations among observed vari(cid:173) ables. I propose a simple unit that adds zero-mean Gaussian noise to its input before passing it through a sigmoidal squashing func(cid:173) tion. Such units can produce a variety of useful behaviors, ranging from deterministic to binary stochastic to continuous stochastic. I show how "slice sampling" can be used for inference and learning in top-down networks of these units and demonstrate learning on two simple problems.
Cite
Text
Frey. "Continuous Sigmoidal Belief Networks Trained Using Slice Sampling." Neural Information Processing Systems, 1996.Markdown
[Frey. "Continuous Sigmoidal Belief Networks Trained Using Slice Sampling." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/frey1996neurips-continuous/)BibTeX
@inproceedings{frey1996neurips-continuous,
title = {{Continuous Sigmoidal Belief Networks Trained Using Slice Sampling}},
author = {Frey, Brendan J.},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {452-458},
url = {https://mlanthology.org/neurips/1996/frey1996neurips-continuous/}
}