Uncertainty quantification in neural network classifiers -- a local linear approach
Not on the map. Why?
Abstract (arXiv)
Classifiers based on neural networks (NN) often lack a measure of uncertainty in the predicted class. We propose a method to estimate the probability mass function (PMF) of the different classes, as well as the covariance of the estimated PMF. First, a local linear approach is used during the training phase to recursively compute the covariance of the parameters in the NN. Secondly, in the classification phase another local linear approach is used to propagate the covariance of the learned NN parameters to the uncertainty in the output of the last layer of the NN. This allows for an efficient Monte Carlo (MC) approach for: (i) estimating the PMF; (ii) calculating the covariance of the estimated PMF; and (iii) proper risk assessment and fusion of multiple classifiers. Two classical image classification tasks, i.e., MNIST, and CFAR10, are used to demonstrate the efficiency the proposed method.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 58 references that are in the map. First posted on arXiv 10 Mar 2023.
Builds on
28 of 58 references.
References · 28
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
- 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
- 2015Optimizing Neural Networks with Kronecker-factored Approximate Curvaturecited by 776
- 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
- 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
- 2015Weight Uncertainty in Neural Networkscited by 554
16 more
- 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 488
- 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
- 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
- 2019Evaluating model calibration in classificationcited by 165
- 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
- 2019Practical Deep Learning with Bayesian Principlescited by 158
- 2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 151
- 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
- 2018Bayesian Uncertainty Estimation for Batch Normalized Deep Networkscited by 70
- 2020Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to Endcited by 55
- 2021Dangers of Bayesian Model Averaging under Covariate Shiftcited by 31
- 2022Accelerated Linearized Laplace Approximation for Bayesian Deep Learningcited by 27
- 2016Deep Neural Networks for Improved, Impromptu Trajectory Tracking of Quadrotorscited by 7
- 2022Accurate Prediction and Uncertainty Estimation using Decoupled Prediction Interval Networkscited by 2
- 2022On the sensitivity of pose estimation neural networks: rotation parameterizations, Lipschitz constants, and provable boundscited by 2
- 2022SLOVA: Uncertainty Estimation Using Single Label One-Vs-All Classifiercited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.