Answers are grounded in this paper and cite their sources.
In this note, we show that exponentially deep belief networks can approximate any distribution over binary vectors to arbitrary accuracy, even when the width of each layer is limited to the dimensionality of the data. We further show that such networks can be greedily learned in an easy yet impractical way.
No takes yet. Share an insight, caveat, or question.
Sutskever et al. (2008) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: