和积网络:一种新的深层结构
Sum-Product Networks: A New Deep Architecture
摘要:
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:在什么一般条件下配分函数是易处理的?答案是一种新的深度架构,我们称之为和积网络(SPN)。SPN是有向无环图,其中变量作为叶,和产品作为内部节点,以及加权边。我们表明,如果一个SPN是完整的和一致的,它表示的分区函数和一些图形模型的所有边缘,并给出其节点的语义。基本上所有易于处理的图形模型都可以转换为SPN,但SPN也更一般。然后,我们提出了学习算法的SPN,基于反向传播和EM。实验表明,使用SPN进行推理和学习比使用标准深度网络更快,更准确。例如,对于这项任务,SPN比最先进的深度网络更好地执行图像完成。SPNs也与大脑皮层的结构有着有趣的潜在联系。
英文摘要:
The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are 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). SPNs are directed acyclic graphs with variables as leaves, sums and products as internal nodes, and weighted edges. We show that if an SPN is complete and consistent it represents the partition function and all marginals of some graphical model, and give semantics to its nodes. Essentially all tractable graphical models can be cast as SPNs, but SPNs are also strictly more general. We then propose learning algorithms for SPNs, based on backpropagation and EM. Experiments show that inference and learning with SPNs can be both faster and more accurate than with standard deep networks. For example, SPNs perform image completion better than state-of-the-art deep networks for this task. SPNs also have intriguing potential connections to the architecture of the cortex.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。