论文标题
使用高维度的投影信念网络
Using the Projected Belief Network at High Dimensions
论文作者
论文摘要
投影信念网络（PBN）是具有可拖动似然函数的分层生成网络（LGN），并且基于馈送前向神经网络（FFNN）。 PBN有两个版本：随机和确定性（D-PBN），每个版本都比其他LGN具有理论上的优势。但是，PBN的实现需要一种迭代算法，该算法包括每个层中大小m x m的对称矩阵的反转，其中m是层输出维度。这，以及网络必须始终在每一层中始终减小维度的事实，可以限制可以应用PBN的问题的类型。在本文中，我们描述了避免或减轻这些限制的技术，并在高维度上有效地使用PBN。我们将歧视的PBN（PBN-DA）应用于声学事件的高维频谱图分类和自动编码。我们还首次介绍了歧视性的D-PBN。
The projected belief network (PBN) is a layered generative network (LGN) with tractable likelihood function, and is based on a feed-forward neural network (FFNN). There are two versions of the PBN: stochastic and deterministic (D-PBN), and each has theoretical advantages over other LGNs. However, implementation of the PBN requires an iterative algorithm that includes the inversion of a symmetric matrix of size M X M in each layer, where M is the layer output dimension. This, and the fact that the network must be always dimension-reducing in each layer, can limit the types of problems where the PBN can be applied. In this paper, we describe techniques to avoid or mitigate these restrictions and use the PBN effectively at high dimension. We apply the discriminatively aligned PBN (PBN-DA) to classifying and auto-encoding high-dimensional spectrograms of acoustic events. We also present the discriminatively aligned D-PBN for the first time.
