期刊
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING
卷 113, 期 -, 页码 303-323出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ijar.2019.07.008
关键词
Bayesian networks; Neural networks; Arithmetic circuits; Function approximation
资金
- NSF [IIS-1514253]
- ONR [N00014-18-1-2561]
- DARPA XAI grant [N66001-17-2-4032]
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. (C) 2019 Elsevier Inc. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据