The Projected Belief Network Classfier : both Generative and Discriminative
This work addresses the challenge of combining generative and discriminative models in neural networks for applications like speech processing, though it appears incremental as it builds on existing PBN and CNN frameworks.
The paper introduced a convolutional projected belief network (PBN) that integrates generative and discriminative capabilities, tested on spoken command spectrograms, achieving classifier performance close to a regularized discriminative network while enabling random data synthesis and reconstruction from hidden variables.
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.