深度信念网络的核和子模型
Kernels and Submodels of Deep Belief Networks
摘要：
研究了随机分层网络中表示为可见边缘分布的分解概率分布的混合。我们从分布的核转换的角度出发，给出了深度信念网络（DBN）和其他没有横向连接的网络的分布式表示的统一画面。我们描述的组合和几何性质的一组内核和产品的内核可实现的DBN的网络参数的变化。我们描述了明确的类概率分布，包括指数族，可以学习的DBN。我们使用这些子模型来限制DBN的最大和预期Kullback-Leibler近似误差，这取决于它们包含的隐藏层和单元的数量。
英文摘要：
We study the mixtures of factorizing probability distributions represented as visible marginal distributions in stochastic layered networks. We take the perspective of kernel transitions of distributions, which gives a unified picture of distributed representations arising from Deep Belief Networks (DBN) and other networks without lateral connections. We describe combinatorial and geometric properties of the set of kernels and products of kernels realizable by DBNs as the network parameters vary. We describe explicit classes of probability distributions, including exponential families, that can be learned by DBNs. We use these submodels to bound the maximal and the expected Kullback-Leibler approximation errors of DBNs from above depending on the number of hidden layers and units that they contain.
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。
