On the Relative Expressiveness of Bayesian and Neural Networks

December 21, 2018 Β· Declared Dead Β· πŸ› European Workshop on Probabilistic Graphical Models

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Arthur Choi, Ruocheng Wang, Adnan Darwiche arXiv ID 1812.08957 Category cs.AI: Artificial Intelligence Cross-listed cs.LG Citations 27 Venue European Workshop on Probabilistic Graphical Models Last Checked 4 months ago
Abstract
A neural network computes a function. A central property of neural networks is that they are "universal approximators:" for a given continuous function, there exists a neural network that can approximate it arbitrarily well, given enough neurons (and some additional assumptions). In contrast, a Bayesian network is a model, but each of its queries can be viewed as computing a function. In this paper, we identify some key distinctions between the functions computed by neural networks and those by marginal Bayesian network queries, showing that the former are more expressive than the latter. Moreover, we propose a simple augmentation to Bayesian networks (a testing operator), which enables their marginal queries to become "universal approximators."
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted