Towards a Better Understanding of Deep Neural Networks Representations using Deep Generative Networks

Jérémie Despraz, Stéphane Gomez, Héctor F. Satizábal, Carlos Andrés Peña-Reyes

Abstract

This paper presents a novel approach to deep-dream-like image generation for convolutional neural networks (CNNs). Images are produced by a deep generative network from a smaller dimensional feature vector. This method allows for the generation of more realistic looking images than traditional activation-maximization methods and gives insight into the CNN’s internal representations. Training is achieved by standard backpropagation algorithms.

Download


Paper Citation


in Harvard Style

Despraz J., Gomez S., Satizábal H. and Peña-Reyes C. (2017). Towards a Better Understanding of Deep Neural Networks Representations using Deep Generative Networks.In Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI, ISBN 978-989-758-274-5, pages 215-222. DOI: 10.5220/0006495102150222


in Bibtex Style

@conference{ijcci17,
author={Jérémie Despraz and Stéphane Gomez and Héctor F. Satizábal and Carlos Andrés Peña-Reyes},
title={Towards a Better Understanding of Deep Neural Networks Representations using Deep Generative Networks},
booktitle={Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,},
year={2017},
pages={215-222},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006495102150222},
isbn={978-989-758-274-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,
TI - Towards a Better Understanding of Deep Neural Networks Representations using Deep Generative Networks
SN - 978-989-758-274-5
AU - Despraz J.
AU - Gomez S.
AU - Satizábal H.
AU - Peña-Reyes C.
PY - 2017
SP - 215
EP - 222
DO - 10.5220/0006495102150222