论文标题
预计的信念网络类：生成和歧视性
The Projected Belief Network Classfier : both Generative and Discriminative
论文作者
论文摘要
投影信念网络（PBN）是一个具有可拖动似然函数的分层生成网络，并且基于馈送前向神经网络（FF-NN）。因此，它可以与判别性分类器共享一个实施例，并可以继承两种网络的最佳素质。在本文中，构造了卷积PBN，该PBN既完全歧视又完全产生，并且在口语命令的频谱图上进行了测试。结果表明，网络从歧视或生成观点中显示出优秀的品质。显示了来自低维隐藏变量的随机数据综合和可见数据重建，而分类器的性能接近正规判别网络的性能。还证明了与常规歧视性CNN的结合。
The projected belief network (PBN) is a layered generative network with tractable likelihood function, and is based on a feed-forward neural network (FF-NN). It can therefore share an embodiment with a discriminative classifier and can inherit the best qualities of both types of network. In this paper, a convolutional PBN is constructed that is both fully discriminative and fully generative and is tested on spectrograms of spoken commands. It is shown that the network displays excellent qualities from either the discriminative or generative viewpoint. Random data synthesis and visible data reconstruction from low-dimensional hidden variables are shown, while classifier performance approaches that of a regularized discriminative network. Combination with a conventional discriminative CNN is also demonstrated.
