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

Jérémie Despraz, Stéphane Gomez, Héctor F. Satizábal, Carlos Andrés Peña-Reyes
2017 Proceedings of the 9th International Joint Conference on Computational Intelligence  
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.
doi:10.5220/0006495102150222 dblp:conf/ijcci/DesprazGSP17 fatcat:smntn4qz6zhvfjuu7a2asjyydq