通过噪声注入实现神经网络不确定性量化，提升预测可信度。
Uncertainty Quantification With Noise Injection in Neural Networks: A Bayesian Perspective
- 从贝叶斯视角证明权重加噪等价于深层高斯过程推断
- 在回归与分类任务中，不确定性估计性能优于基线模型
- 适合需要可靠置信度评估的机器学习应用
模型不确定性量化旨在衡量预测结果相关的不确定性，以评估其可靠性与置信度。噪声注入是一种通过引入随机性来增强神经网络鲁棒性的技术。本文从贝叶斯角度建立噪声注入与不确定性量化的联系，理论上证明在神经网络权重中注入噪声等价于对深层高斯过程进行贝叶斯推断。基于此，提出蒙特卡洛噪声注入（MCNI）方法：训练时注入参数噪声，推理时多次前向传播以估计预测不确定性。在回归与分类任务的仿真与实验中，该方法表现优于基线模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。