Learning the Architecture of Sum-Product Networks Using Clustering on Variables
Learning the Architecture of Sum-Product Networks Using Clustering on Variables
复制标题
DOI：
--
复制
发表时间：
2012-12
期刊：
影响因子：
--
通讯作者：
Aaron W. Dennis;D. Ventura
中科院分区：
文献类型：
--
作者：
Aaron W. Dennis;D. Ventura
和积网络（SPN）是最近提出的一种深度模型，由和和积节点的网络组成，并且已被证明在某些困难任务（例如图像完成）上与最先进的深度模型具有竞争力。设计适合当前任务的 SPN 网络架构是一个悬而未决的问题。我们提出了一种从数据中学习 SPN 架构的算法。这个想法是对变量进行聚类（而不是数据实例），以便识别彼此强烈交互的变量子集。然后分配 SPN 网络中的节点来解释这些交互。实验证据表明，与使用先前提出的静态架构相比，学习 SPN 架构可显着提高其性能。
The sum-product network (SPN) is a recently-proposed deep model consisting of a network of sum and product nodes, and has been shown to be competitive with state-of-the-art deep models on certain difficult tasks such as image completion. Designing an SPN network architecture that is suitable for the task at hand is an open question. We propose an algorithm for learning the SPN architecture from data. The idea is to cluster variables (as opposed to data instances) in order to identify variable subsets that strongly interact with one another. Nodes in the SPN network are then allocated towards explaining these interactions. Experimental evidence shows that learning the SPN architecture significantly improves its performance compared to using a previously-proposed static architecture.