Richard Bamler

Papers

Total Citations

1,134

H-Index

About

Richard Bamler is a leading researcher at the intersection of deep learning and uncertainty quantification, best known for his foundational work on understanding and measuring uncertainty in neural network predictions. His landmark survey, "A survey of uncertainty in deep neural networks" (2023), has already garnered over 1,100 citations, establishing itself as a go-to reference for researchers and practitioners alike. In this comprehensive work, Bamler systematically categorizes sources of uncertainty—aleatoric and epistemic—and reviews state-of-the-art methods for their estimation, including Bayesian neural networks, ensemble techniques, and variational inference. His contributions have been instrumental in making deep learning models more reliable and interpretable, particularly in high-stakes domains such as healthcare, autonomous driving, and finance. Beyond his survey, Bamler has advanced probabilistic machine learning through novel algorithms that balance computational efficiency with rigorous uncertainty modeling. His work continues to shape how the field approaches model confidence, robustness, and decision-making under uncertainty, making him a key voice for students and researchers seeking to build trustworthy AI systems.