Defending against adversarial examples with GloRo Nets — Over the last several years, deep networks have extensively been shown to be vulnerable to attackers that can cause the network to make perplexing mistakes, simply by feeding maliciously-perturbed inputs to the network. Clearly, this raises concrete safety concerns for neural networks deployed in the wild, especially in safety-critical settings…

How feature usage informs our understanding of overfitting in deep networks — Overfitting is a central problem in machine learning that is strongly tied to the reliability of a learned model when it is deployed on unseen data. Overfitting is often measured — or even defined — by the difference in accuracy obtained by a model on its training data, compared to…

How feature usage informs our understanding of overfitting in deep networks — Overfitting is a central problem in machine learning that is strongly tied to the reliability of a learned model when it is deployed on unseen data. Overfitting is often measured — or even defined — by the difference in accuracy obtained by a model on its training data, compared to…

Transparency and Attribution Methods In recent years, deep learning has become increasingly powerful and ubiquitous; while at the same time, its inner workings are far from well-understood. As the application of ML has increased, so has the need for algorithmic transparency, the ability to understand why algorithms deployed in the real world make the…