Search Results for author:
Found 4 papers, 4 papers with code
Neuro-Inspired Deep Neural Networks with Sparse, Strong Activations
While end-to-end training of Deep Neural Networks (DNNs) yields state of the art performance in an increasing array of applications, it does not provide insight into, or control over, the features being extracted.
Sparse Coding Frontend for Robust Neural Networks
Deep Neural Networks are known to be vulnerable to small, adversarially crafted, perturbations.
A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations
Our nominal design is to train the decoder and classifier together in standard supervised fashion, but we also consider unsupervised decoder training based on a regression objective (as in a conventional autoencoder) with separate supervised training of the classifier.
Polarizing Front Ends for Robust CNNs
The vulnerability of deep neural networks to small, adversarially designed perturbations can be attributed to their "excessive linearity."
