Sight-seeing in the eyes of deep neural networks

We address the interpretability of convolutional neural networks (CNNs) for predicting a geo-location from an image. In a pilot experiment we classify images of Pittsburgh vs Tokyo and visualize the learned CNN filters. We found that varying the CNN architecture leads to variating in the visualized filters. This calls for further investigation of the effective parameters on the interpretability of CNNs.
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Pattern Recognition and Bioinformatics
History & Complexity