Improved Classification Based on Deep Belief Networks

For better classification generative models are used to initialize the model and model features before training a classifier. Typically it is needed to solve separate unsupervised and supervised learning problems. Generative restricted Boltzmann machines and deep belief networks are widely used for...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Koo, Jaehoon, Klabjan, Diego
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 12.08.2019
Subjects
Belief networks
Classification
Mathematical models
Training
Weight
Online AccessGet full text

Cover

More Information
Summary:For better classification generative models are used to initialize the model and model features before training a classifier. Typically it is needed to solve separate unsupervised and supervised learning problems. Generative restricted Boltzmann machines and deep belief networks are widely used for unsupervised learning. We developed several supervised models based on DBN in order to improve this two-phase strategy. Modifying the loss function to account for expectation with respect to the underlying generative model, introducing weight bounds, and multi-level programming are applied in model development. The proposed models capture both unsupervised and supervised objectives effectively. The computational study verifies that our models perform better than the two-phase training approach.
ISSN:2331-8422