Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness

1 code implementation • 9 Oct 2023 • Bhavya Vasudeva, Kameron Shahabi, Vatsal Sharan

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative.

Fairness

Towards Accurate Spatiotemporal COVID-19 Risk Scores using High Resolution Real-World Mobility Data

1 code implementation • 14 Dec 2020 • Sirisha Rambhatla, Sepanta Zeighami, Kameron Shahabi, Cyrus Shahabi, Yan Liu

As countries look towards re-opening of economic activities amidst the ongoing COVID-19 pandemic, ensuring public health has been challenging.