The Projected Belief Network Classfier : both Generative and Discriminative

08/14/2020
by   Paul M. Baggenstoss, et al.
0

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.

READ FULL TEXT
research
04/25/2022

Using the Projected Belief Network at High Dimensions

The projected belief network (PBN) is a layered generative network (LGN)...
research
06/21/2016

Kernel-based Generative Learning in Distortion Feature Space

This paper presents a novel kernel-based generative classifier which is ...
research
03/05/2017

Diversified Texture Synthesis with Feed-forward Networks

Recent progresses on deep discriminative and generative modeling have sh...
research
04/25/2017

Introspective Classifier Learning: Empower Generatively

In this paper we propose introspective classifier learning (ICL) that em...
research
05/10/2023

A Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layer

Generative models have advantageous characteristics for classification t...
research
04/08/2023

Exploring the Connection between Robust and Generative Models

We offer a study that connects robust discriminative classifiers trained...
research
02/16/2022

Generative modeling with projected entangled-pair states

We argue and demonstrate that projected entangled-pair states (PEPS) out...

Please sign up or login with your details

Forgot password? Click here to reset