arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.07359cs.AIcs.LGphysics.hist-ph
收藏

科学与深度学习中的可靠性与可解释性

Reliability and Interpretability in Science and Deep Learning

Accenture AG(埃森哲股份公司)

Luigi Scorzato

AI总结:

本文从认识论角度比较传统科学模型与深度神经网络模型,论证DNN模型的高认识论复杂性会妨碍可靠性评估与长期进步,并阐明可解释性是评估模型可靠性的前提,不能仅依赖统计分析。

摘要:

近年来,机器学习(ML)方法的可靠性问题已变得极为重要,对相关不确定性的分析推动了越来越多的研究。然而,这些研究大多将标准误差分析应用于机器学习模型,尤其是深度神经网络(DNN)模型,而这与标准科学建模存在相当显著的差异。因此,有必要将标准误差分析与更深入的认识论分析相结合,以考察DNN模型与标准科学建模之间可能存在的差异,以及这些差异对可靠性评估可能产生的影响。本文提供了若干贡献。首先,本文强调模型假设(在机器学习和传统科学中)无处不在的作用,以反对无理论科学的幻象。其次,从模型假设的(认识论)复杂性角度对其进行分析,并表明这种复杂性是与语言无关的。本文论证,DNN模型的高认识论复杂性妨碍了对其可靠性的估计,也妨碍了其长期进步的前景。文中提出了一些可能的改进方向。第三,本文指出了模型的认识论复杂性与可解释性之间的密切关系,这一概念是在负责任人工智能的背景下引入的。这澄清了在何种意义上以及在多大程度上,对模型缺乏理解(黑箱问题)会以一种独立于个人技能的方式影响其可解释性。本文还阐明了可解释性为何是评估任何模型可靠性的前提条件,而可靠性不能仅建立在统计分析之上。本文重点关注传统科学模型与DNN模型之间的比较。不过,随机森林和逻辑回归模型也被简要考虑。

英文摘要:

In recent years, the question of the reliability of Machine Learning (ML) methods has acquired significant importance, and the analysis of the associated uncertainties has motivated a growing amount of research. However, most of these studies have applied standard error analysis to ML models, and in particular Deep Neural Network (DNN) models, which represent a rather significant departure from standard scientific modelling. It is therefore necessary to integrate the standard error analysis with a deeper epistemological analysis of the possible differences between DNN models and standard scientific modelling and the possible implications of these differences in the assessment of reliability. This article offers several contributions. First, it emphasises the ubiquitous role of model assumptions (both in ML and traditional Science) against the illusion of theory-free science. Secondly, model assumptions are analysed from the point of view of their (epistemic) complexity, which is shown to be language-independent. It is argued that the high epistemic complexity of DNN models hinders the estimate of their reliability and also their prospect of long-term progress. Some potential ways forward are suggested. Thirdly, this article identifies the close relation between a model's epistemic complexity and its interpretability, as introduced in the context of responsible AI. This clarifies in which sense, and to what extent, the lack of understanding of a model (black-box problem) impacts its interpretability in a way that is independent of individual skills. It also clarifies how interpretability is a precondition for assessing the reliability of any model, which cannot be based on statistical analysis alone. This article focuses on the comparison between traditional scientific models and DNN models. But, Random Forest and Logistic Regression models are also briefly considered.

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。

↑