Uncertainty Aware Neural Network from Similarity and Sensitivity

Abstract

Researchers have proposed several approaches for neural network (NN) based uncertainty quantification (UQ). However, most of the approaches are developed considering strong assumptions. Uncertainty quantification algorithms often perform poorly in an input domain and the reason for poor performance remains unknown. Therefore, we present a neural network training method that considers similar samples with sensitivity awareness in this paper. In the proposed NN training method for UQ, first, we train a shallow NN for the point prediction. Then, we compute the absolute differences between prediction and targets and train another NN for predicting those absolute differences or absolute errors. Domains with high average absolute errors represent a high uncertainty. In the next step, we select each sample in the training set one by one and compute both prediction and error sensitivities. Then we select similar samples with sensitivity consideration and save indexes of similar samples. The ranges of an input parameter become narrower when the output is highly sensitive to that parameter. After that, we construct initial uncertainty bounds (UB) by considering the distribution of sensitivity aware similar samples. Prediction intervals (PIs) from initial uncertainty bounds are larger and cover more samples than required. Therefore, we train bound correction NN. As following all the steps for finding UB for each sample requires a lot of computation and memory access, we train a UB computation NN. The UB computation NN takes an input sample and provides an uncertainty bound. The UB computation NN is the final product of the proposed approach. Scripts of the proposed method are available in the following GitHub repository: github.com/dipuk0506/UQ

References in corpus (7)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
• A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
• Towards a mathematical framework to inform Neural Network modelling via Polynomial Regression
• Reduction of Class Activation Uncertainty with Background Information
• Evaluating State-of-the-Art Classification Models Against Bayes Optimality
• Artificial Intelligence for Dynamical Systems in Wireless Communications: Modeling for the Future

Cited by in corpus (1)

• How to Evaluate Uncertainty Estimates in Machine Learning for Regression?