Probabilistic Neural Networks (PNNs) for Modeling Aleatoric Uncertainty in Scientific Machine Learning
Not on the map. Why?
Abstract (arXiv)
This paper investigates the use of probabilistic neural networks (PNNs) to model aleatoric uncertainty, which refers to the inherent variability in the input-output relationships of a system, often characterized by unequal variance or heteroscedasticity. Unlike traditional neural networks that produce deterministic outputs, PNNs generate probability distributions for the target variable, allowing the determination of both predicted means and intervals in regression scenarios. Contributions of this paper include the development of a probabilistic distance metric to optimize PNN architecture, and the deployment of PNNs in controlled data sets as well as a practical material science case involving fiber-reinforced composites. The findings confirm that PNNs effectively model aleatoric uncertainty, proving to be more appropriate than the commonly employed Gaussian process regression for this purpose. Specifically, in a real-world scientific machine learning context, PNNs yield remarkably accurate output mean estimates with R-squared scores approaching 0.97, and their predicted intervals exhibit a high correlation coefficient of nearly 0.80, closely matching observed data intervals. Hence, this research contributes to the ongoing exploration of leveraging the sophisticated representational capacity of neural networks to delineate complex input-output relationships in scientific problems.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 22 of its 55 references that are in the map. First posted on arXiv 21 Feb 2024.
Builds on
22 of 55 references.
References · 22
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
- 2016On the Expressive Power of Deep Neural Networkscited by 302
- 2019Predictive inference with the jackknife+cited by 206
- 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
- 2020Deep Network Approximation for Smooth Functionscited by 163
- 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
- 2020Improving data-driven global weather prediction using deep convolutional neural networks on a cubed spherecited by 95
- 2021Scientific Machine Learning Benchmarkscited by 60
- 2020The gap between theory and practice in function approximation with deep neural networkscited by 53
- 2017Variants of RMSProp and Adagrad with Logarithmic Regret Boundscited by 50
- 2022Faithful Heteroscedastic Regression with Neural Networkscited by 36
- 2022How important are activation functions in regression and classification? A survey, performance comparison, and future directionscited by 29
10 more
- 2023Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorialcited by 27
- 2022Bayesian Learning for Neural Networks: an algorithmic surveycited by 22
- 2020Machine Learning Information Fusion in Earth Observation: A Comprehensive Review of Methods, Applications and Data Sourcescited by 19
- 2022Maximum Likelihood Estimation in Gaussian Process Regression is Ill-Posedcited by 16
- 2021Probabilistic Deep Learning for Real-Time Large Deformation Simulationscited by 11
- 2021SERF: Towards better training of deep neural networks using log-Softplus ERror activation Functioncited by 10
- 2022Low-Precision Arithmetic for Fast Gaussian Processescited by 10
- 2022Variational Neural Networkscited by 7
- 2022Estimating Regression Predictive Distributions with Sample Networkscited by 4
- 2017Improved Fixed-Rank Nystr"om Approximation via QR Decomposition: Practical and Theoretical Aspectscited by 3
Built on by
Citing papers per year: 2025: 2.
2 papers.