deletions | additions       diff --git a/bibliography/biblio.bib b/bibliography/biblio.bib  index 27367fc..2427d13 100644  --- a/bibliography/biblio.bib  +++ b/bibliography/biblio.bib 
...
keywords = {Computer Science - Computer Vision and Pattern Recognition},  file = {arXiv\:1409.1556 PDF:C\:\\Users\\yunfuliu\\AppData\\Roaming\\Zotero\\Zotero\\Profiles\\yx5a4mz5.default\\zotero\\storage\\KFU2778D\\Simonyan 與 Zisserman - 2014 - Very Deep Convolutional Networks for Large-Scale I.pdf:application/pdf;arXiv.org Snapshot:C\:\\Users\\yunfuliu\\AppData\\Roaming\\Zotero\\Zotero\\Profiles\\yx5a4mz5.default\\zotero\\storage\\4ZREHXT7\\1409.html:text/html},  }  @article{zeiler_visualizing_2013,  title = {{Visualizing and {Understanding} {Convolutional} {Networks}}},  url = {http://arxiv.org/abs/1311.2901},  abstract = {Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we address both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. We also perform an ablation study to discover the performance contribution from different model layers. This enables us to find model architectures that outperform Krizhevsky {\textbackslash}etal on the ImageNet classification benchmark. We show our ImageNet model generalizes well to other datasets: when the softmax classifier is retrained, it convincingly beats the current state-of-the-art results on Caltech-101 and Caltech-256 datasets.},  urldate = {2015-08-30},  journal = {arXiv:1311.2901 [cs]},  author = {Zeiler, Matthew D. and Fergus, Rob},  month = {nov},  year = {2013},  note = {arXiv: 1311.2901},  keywords = {Computer Science - Computer Vision and Pattern Recognition},  file = {arXiv.org Snapshot:C\:\\Users\\yunfuliu\\AppData\\Roaming\\Zotero\\Zotero\\Profiles\\yx5a4mz5.default\\zotero\\storage\\5HDNX7FQ\\1311.html:text/html},  }