Uncertainty Quantification With Noise Injection in Neural Networks: A Bayesian Perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yuan, Xueqiong, Li, Jipeng, Kuruoglu, Ercan Engin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916704805715968
author Yuan, Xueqiong
Li, Jipeng
Kuruoglu, Ercan Engin
author_facet Yuan, Xueqiong
Li, Jipeng
Kuruoglu, Ercan Engin
contents Model uncertainty quantification involves measuring and evaluating the uncertainty linked to a model's predictions, helping assess their reliability and confidence. Noise injection is a technique used to enhance the robustness of neural networks by introducing randomness. In this paper, we establish a connection between noise injection and uncertainty quantification from a Bayesian standpoint. We theoretically demonstrate that injecting noise into the weights of a neural network is equivalent to Bayesian inference on a deep Gaussian process. Consequently, we introduce a Monte Carlo Noise Injection (MCNI) method, which involves injecting noise into the parameters during training and performing multiple forward propagations during inference to estimate the uncertainty of the prediction. Through simulation and experiments on regression and classification tasks, our method demonstrates superior performance compared to the baseline model.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12314
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty Quantification With Noise Injection in Neural Networks: A Bayesian Perspective
Yuan, Xueqiong
Li, Jipeng
Kuruoglu, Ercan Engin
Machine Learning
Model uncertainty quantification involves measuring and evaluating the uncertainty linked to a model's predictions, helping assess their reliability and confidence. Noise injection is a technique used to enhance the robustness of neural networks by introducing randomness. In this paper, we establish a connection between noise injection and uncertainty quantification from a Bayesian standpoint. We theoretically demonstrate that injecting noise into the weights of a neural network is equivalent to Bayesian inference on a deep Gaussian process. Consequently, we introduce a Monte Carlo Noise Injection (MCNI) method, which involves injecting noise into the parameters during training and performing multiple forward propagations during inference to estimate the uncertainty of the prediction. Through simulation and experiments on regression and classification tasks, our method demonstrates superior performance compared to the baseline model.
title Uncertainty Quantification With Noise Injection in Neural Networks: A Bayesian Perspective
topic Machine Learning
url https://arxiv.org/abs/2501.12314