# The Projected Belief Network Classfier : both Generative and Discriminative

arXiv: https://arxiv.org/abs/2008.06434 · HTML: https://mlsanity.com/paper/2008.06434/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2020.

## Built on by (most cited first, 2 of 2)

- [Using the Projected Belief Network at High Dimensions](https://mlsanity.com/paper/2204.12922/) (2022)
- [Maximum Entropy Auto-Encoding](https://mlsanity.com/paper/2104.07448/) (2021)

## Abstract (arXiv)

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.