探究贝叶斯神经网络能否显式建模输入不确定性
Can Bayesian Neural Networks Explicitly Model Input Uncertainty?
- 构建均值与标准差双输入网络，显式建模输入不确定性
- 仅集成方法和Flipout能有效捕捉输入不确定性
- 为选择合适不确定性估计方法提供实证依据
机器学习模型的输入常伴随噪声或不确定性，但通常被忽略。现有研究尚不清楚贝叶斯神经网络及其近似方法是否能有效建模输入不确定性。本文构建了一个双输入贝叶斯神经网络（输入为均值和标准差），并在多种近似方法（如集成、MC-Dropout、Flipout）下评估其输入不确定性估计能力。结果表明，仅有集成方法和Flipout能够有效建模输入不确定性，其他方法表现不佳。
原文摘要 · Abstract (English)
Inputs to machine learning models can have associated noise or uncertainties, but they are often ignored and not modelled. It is unknown if Bayesian Neural Networks and their approximations are able to consider uncertainty in their inputs. In this paper we build a two input Bayesian Neural Network (mean and standard deviation) and evaluate its capabilities for input uncertainty estimation across different methods like Ensembles, MC-Dropout, and Flipout. Our results indicate that only some uncertainty estimation methods for approximate Bayesian NNs can model input uncertainty, in particular Ensembles and Flipout.
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。