arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.18787cs.LGstat.ML
收藏

统一的不确定性:将输入、数据和模型不确定性结合到单一公式中

Unified Uncertainties: Combining Input, Data and Model Uncertainty into a Single Formulation

University of Groningen(格罗宁根大学)

Matias Valdenegro-Toro, Ivo Pascal de Jong, Marco Zullich

AI总结:

提出一种通过神经网络传播输入不确定性的方法,可同时估计输入、数据和模型不确定性,相比Monte Carlo采样在大量噪声下决策边界更稳定,并证明输入不确定性传播会产生输出模型不确定性。

摘要:

对机器学习模型中的不确定性进行建模对于实现安全可靠的预测至关重要。大多数关于不确定性的研究集中在输出不确定性(预测)上,但对输入端的不确定性关注甚少。我们提出了一种通过神经网络传播输入不确定性的方法,该方法能够同时估计输入、数据和模型不确定性。我们的结果表明,与相对简单的Monte Carlo采样相比,这种输入不确定性的传播即使在大量输入噪声下也能产生更稳定的决策边界。此外,我们讨论并证明了输入不确定性在通过模型传播时会在输出端产生模型不确定性。在已知输入不确定性大小的情况下,显式地纳入输入不确定性可能是有益的,尽管仍需要为此提供良好的数据集。

英文摘要:

Modelling uncertainty in Machine Learning models is essential for achieving safe and reliable predictions. Most research on uncertainty focuses on output uncertainty (predictions), but minimal attention is paid to uncertainty at inputs. We propose a method for propagating uncertainty in the inputs through a Neural Network that is simultaneously able to estimate input, data, and model uncertainty. Our results show that this propagation of input uncertainty results in a more stable decision boundary even under large amounts of input noise than comparatively simple Monte Carlo sampling. Additionally, we discuss and demonstrate that input uncertainty, when propagated through the model, results in model uncertainty at the outputs. The explicit incorporation of input uncertainty may be beneficial in situations where the amount of input uncertainty is known, though good datasets for this are still needed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑