Sum-product networks: A new deep architecture

Sum-product networks: A new deep architecture
复制标题

DOI:
10.1109/iccvw.2011.6130310
复制
发表时间:
2011-07
期刊:
2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)
影响因子:
--
通讯作者:
Hoifung Poon;Pedro M. Domingos
Hoifung Poon;Pedro M. Domingos
中科院分区:
其他
文献类型:
--
作者:
Hoifung Poon;Pedro M. Domingos

文献摘要

被引文献

相似文献

图模型推理和学习的关键限制因素是划分函数的复杂性。因此,我们提出这样一个问题:在什么样的最一般的条件下配分函数是易处理的?答案是一种新的深层架构,我们称之为和积网络(SPN),并将在本摘要中介绍。
The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are the most general conditions under which the partition function is tractable? The answer leads to a new kind of deep architecture, which we call sum-product networks (SPNs) and will present in this abstract.