Workshop

Uncertainty and Robustness in Deep Learning Workshop (UDL)

Sharon Yixuan Li, Balaji Lakshminarayanan, Dan Hendrycks, Tom Dietterich, Jasper Snoek

Keywords:  • Model uncertainty estimation and calibration    • Probabilistic (Bayesian and non-Bayesian) neural networks    • Anomaly detection and out-of-distribution detection    • Robustness to distribution shift    • Model misspecification    • Quantifying different types of uncertainty    • Open world recognition  

Abstract:

There has been growing interest in rectifying deep neural network instabilities. Challenges arise when models receive samples drawn from outside the training distribution. For example, a neural network tasked with classifying handwritten digits may assign high confidence predictions to cat images. Anomalies are frequently encountered when deploying ML models in the real world. Well-calibrated predictive uncertainty estimates are indispensable for many machine learning applications, such as self-driving vehicles and medical diagnosis systems. Generalization to unseen and worst-case inputs is also essential for robustness to distributional shift. In order to have ML models reliably predict in open environment, we must deepen technical understanding in the emerging areas of: (1) learning algorithms that can detect changes in data distribution (e.g. out-of-distribution examples); (2) mechanisms to estimate and calibrate confidence produced by neural networks in typical and unforeseen scenarios; (3) methods to improve out-of-distribution generalization, including generalization to temporal, geographical, hardware, adversarial, and image-quality changes; (4) benchmark datasets and protocols for evaluating model performance under distribution shift; and (5) key applications of robust and uncertainty-aware deep learning (e.g., computer vision, robotics, self-driving vehicles, medical imaging) as well as broader machine learning tasks.

This workshop will bring together researchers and practitioners from the machine learning communities, and highlight recent work that contributes to addressing these challenges. Our agenda will feature contributed papers with invited speakers. Through the workshop we hope to help identify fundamentally important directions on robust and reliable deep learning, and foster future collaborations.

Live content is unavailable. Are you logged in?

Timezone: »

Schedule

Are you logged in?