A tutorial on calibration measurements and calibration models for clinical prediction models
Our primary objective is to provide the clinical informatics community with an introductory
tutorial on calibration measurements and calibration models for predictive models using …
tutorial on calibration measurements and calibration models for predictive models using …
Revisiting the calibration of modern neural networks
Accurate estimation of predictive uncertainty (model calibration) is essential for the safe
application of neural networks. Many instances of miscalibration in modern neural networks …
application of neural networks. Many instances of miscalibration in modern neural networks …
How can we know what language models know?
Recent work has presented intriguing results examining the knowledge contained in
language models (LMs) by having the LM fill in the blanks of prompts such as “Obama is a …
language models (LMs) by having the LM fill in the blanks of prompts such as “Obama is a …
How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering
Recent works have shown that language models (LM) capture different types of knowledge
regarding facts or common sense. However, because no model is perfect, they still fail to …
regarding facts or common sense. However, because no model is perfect, they still fail to …
Improving calibration for long-tailed recognition
Deep neural networks may perform poorly when training datasets are heavily class-
imbalanced. Recently, two-stage methods decouple representation learning and classifier …
imbalanced. Recently, two-stage methods decouple representation learning and classifier …
Accurate uncertainties for deep learning using calibrated regression
V Kuleshov, N Fenner, S Ermon - … conference on machine …, 2018 - proceedings.mlr.press
Methods for reasoning under uncertainty are a key building block of accurate and reliable
machine learning systems. Bayesian methods provide a general framework to quantify …
machine learning systems. Bayesian methods provide a general framework to quantify …
Verified uncertainty calibration
Applications such as weather forecasting and personalized medicine demand models that
output calibrated probability estimates---those representative of the true likelihood of a …
output calibrated probability estimates---those representative of the true likelihood of a …
[PDF][PDF] Measuring Calibration in Deep Learning.
J Nixon, MW Dusenberry, L Zhang… - CVPR …, 2019 - openaccess.thecvf.com
The reliability of a machine learning model's confidence in its predictions is critical for high-
risk applications. Calibration—the idea that a model's predicted probabilities of outcomes …
risk applications. Calibration—the idea that a model's predicted probabilities of outcomes …
On calibration of modern neural networks
Confidence calibration–the problem of predicting probability estimates representative of the
true correctness likelihood–is important for classification models in many applications. We …
true correctness likelihood–is important for classification models in many applications. We …
Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning
N Papernot, P McDaniel - arXiv preprint arXiv:1803.04765, 2018 - arxiv.org
Deep neural networks (DNNs) enable innovative applications of machine learning like
image recognition, machine translation, or malware detection. However, deep learning is …
image recognition, machine translation, or malware detection. However, deep learning is …