arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.14552cs.LGstat.ML
收藏

具有随机激活函数的抗差不确定性估计

Toward Robust Uncertainty Estimation with Random Activation Functions

Eindhoven University of Technology(埃因霍温理工大学)

Yana Stoyanova, Soroush Ghandi, Maryam Tavakol

摘要:

深度神经网络因其在许多数据驱动应用中的出色性能而成为机器学习的焦点。然而,当在分布外的数据点中查询时,它们可能导致不准确的预测,这可能具有不利影响,特别是在敏感领域,例如医疗保健和运输,其中错误的预测可能非常昂贵和/或危险。随后,量化神经网络输出的不确定性通常被用来评估其预测的置信度,并且集成模型已经被证明可以通过利用模型池上的预测方差来有效地测量不确定性。在本文中,我们提出了一种新的方法,通过集成的不确定性量化,称为随机激活函数(RAFs)Ensemble,其目的是提高集成的多样性朝着一个更强大的估计,通过容纳每个神经网络与不同的(随机)激活函数。广泛的实证研究表明,RAFs Encriminal优于国家的最先进的集合不确定性量化方法在合成和真实世界的数据集在一系列的回归任务。

英文摘要:

Deep neural networks are in the limelight of machine learning with their excellent performance in many data-driven applications. However, they can lead to inaccurate predictions when queried in out-of-distribution data points, which can have detrimental effects especially in sensitive domains, such as healthcare and transportation, where erroneous predictions can be very costly and/or dangerous. Subsequently, quantifying the uncertainty of the output of a neural network is often leveraged to evaluate the confidence of its predictions, and ensemble models have proved to be effective in measuring the uncertainty by utilizing the variance of predictions over a pool of models. In this paper, we propose a novel approach for uncertainty quantification via ensembles, called Random Activation Functions (RAFs) Ensemble, that aims at improving the ensemble diversity toward a more robust estimation, by accommodating each neural network with a different (random) activation function. Extensive empirical study demonstrates that RAFs Ensemble outperforms state-of-the-art ensemble uncertainty quantification methods on both synthetic and real-world datasets in a series of regression tasks.

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。

↑