Jérémie Despraz presented at the International Joint Conference on Computational Intelligence
Towards a Better Understanding of Deep Neural Networks Representations using Deep Generative Networks
Jérémie Despraz 1,2, Stéphane Gomez 1,2, Héctor F. Satizábal 1, and Carlos Peña-Reyes 1,2
1 School of Business and Engineering Vaud (HEIG-VD), University of Applied Sciences of Western Switzerland (HES-SO), Yverdon-les-Bains, Switzerland
2 Computational Intelligence for Computational Biology (CI4CB), SIB Swiss Institute of Bioinformatics, Lausanne, Switzerland
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: TBD (will be published here)