On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
Author(s)
Cheney, Nicholas; Schrimpf, Martin; Kreiman, Gabriel![Thumbnail](/bitstream/handle/1721.1/107935/CBMM-Memo-065.pdf.jpg?sequence=5&isAllowed=y)
DownloadCBMM-Memo-065.pdf (687.7Kb)
Terms of use
Metadata
Show full item recordAbstract
Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of convolutional neural networks to perturbations to the internal weights and architecture of the network itself. We show that convolutional networks are surprisingly robust to a number of internal perturbations in the higher convolutional layers but the bottom convolutional layers are much more fragile. For instance, Alexnet shows less than a 30% decrease in classification performance when randomly removing over 70% of weight connections in the top convolutional or dense layers but performance is almost at chance with the same perturbation in the first convolutional layer. Finally, we suggest further investigations which could continue to inform the robustness of convolutional networks to internal perturbations.
Date issued
2017-04-03Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1703.08245
Series/Report no.
CBMM Memo Series;065
Collections
The following license files are associated with this item: