paper-with-me

Papers

On Calibrated Model Uncertainty in Deep Learning

2022-06-15 · Biraja Ghoshal, Allan Tucker

Estimated uncertainty by approximate posteriors in Bayesian neural networks are prone to miscalibration, which leads to overconfident predictions in critical tasks that have a clear asymmetric cost or significant losses. Here, we extend the approximate inference for the loss-calibrated Bayesian framework to dropweights based Bayesian neural networks by maximising expected utility over a model posterior to calibrate uncertainty in deep learning. Furthermore, we show that decisions informed by loss-calibrated uncertainty can improve diagnostic performance to a greater extent than straightforward alternatives. We propose Maximum Uncertainty Calibration Error (MUCE) as a metric to measure calibrated confidence, in addition to its prediction especially for high-risk applications, where the goal is to minimise the worst-case deviation between error and estimated uncertainty. In experiments, we show the correlation between error in prediction and estimated uncertainty by interpreting Wasserstein distance as the accuracy of prediction. We evaluated the effectiveness of our approach to detecting Covid-19 from X-Ray images. Experimental results show that our method reduces miscalibration considerably, without impacting the models accuracy and improves reliability of computer-based diagnostics.

📄 PDF Abstract BibTeX arXiv:2206.07795

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningDiagnosticmodelPrediction

Similar Papers 제목 키워드 기반

From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty

2026-03-06 · Azza Jenane, Nassim Walha, Lukas Kuhn, Florian Buettner arxiv

Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore …

Reinforcement Learning

Teaching Models to Express Their Uncertainty in Words

2022-05-28 · Stephanie Lin, Jacob Hilton, Owain Evans

We show that a GPT-3 model can learn to express uncertainty about its own answers in natural language -- without use of model logits. When given a question, the model generates both an answer and a level of confidence (e…

Calibrated Uncertainty for Molecular Property Prediction using Ensembles of Message Passing Neural Networks

2021-07-13 · Jonas Busk, Peter Bjørn Jørgensen, Arghya Bhowmik, Mikkel N. Schmidt 외

Data-driven methods based on machine learning have the potential to accelerate computational analysis of atomic structures. In this context, reliable uncertainty estimates are important for assessing confidence in predic…

BIG-bench Machine LearningDecision MakingMolecular Property PredictionProperty Prediction

Fast Calibrated Explanations: Efficient and Uncertainty-Aware Explanations for Machine Learning Models

2024-10-28 · Tuwe Löfström, Fatima Rabia Yapicioglu, Alessandra Stramiglio, Helena Löfström 외

This paper introduces Fast Calibrated Explanations, a method designed for generating rapid, uncertainty-aware explanations for machine learning models. By incorporating perturbation techniques from ConformaSight - a glob…

Computational EfficiencyFeature ImportanceregressionUncertainty Quantification

Likelihood Annealing: Fast Calibrated Uncertainty for Regression

2023-02-21 · Uddeshya Upadhyay, Jae Myung Kim, Cordelia Schmidt, Bernhard Schölkopf 외

Recent advances in deep learning have shown that uncertainty estimation is becoming increasingly important in applications such as medical imaging, natural language processing, and autonomous systems. However, accurately…

DenoisingImage Super-ResolutionProperty Predictionregression+1