Ben Poole

Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

2019 · arXiv (Cornell University)

Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have led to improved accuracy, building robust models remains challenging. Prior …

Continual Learning Through Synaptic Intelligence

2017 · arXiv (Cornell University)

While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to changing …