Uncertainty Quantification
Uncertainty quantification (UQ) aims to assess and represent the confidence in predictions made by machine learning models, crucial for high-stakes applications where reliable predictions are paramount. Current research focuses on developing robust UQ methods, particularly addressing biases in predictions and efficiently quantifying uncertainty in large language models and deep neural networks, often employing techniques like conformal prediction, Bayesian methods, and ensemble learning. The ability to reliably quantify uncertainty enhances the trustworthiness and applicability of machine learning across diverse fields, from healthcare diagnostics and autonomous driving to climate modeling and drug discovery.
487papers
Papers - Page 25
February 7, 2023
February 2, 2023
Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications
Benchmarking Probabilistic Deep Learning Methods for License Plate Recognition
Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
Physics Constrained Motion Prediction with Uncertainty Quantification
Randomized prior wavelet neural operator for uncertainty quantification
January 18, 2023
January 13, 2023
December 28, 2022
December 24, 2022
December 20, 2022
December 15, 2022
December 14, 2022
December 8, 2022