INTERPRETABILITY in Chinese translation

• 可解释性
• 解释能力

Examples of using Interpretability in English and their translations into Chinese

If we succeed, interpretability promises to be a powerful tool in enabling meaningful human oversight and in building fair, safe, and aligned AI systems.
如果我们取得了成功，可解释性将成为一个强有力的工具，使我们能够实现有意义的人类监督，并建立公平、安全和一致的人工智能系统。

Worse, many interpretability techniques have not been fully actualized into abstractions because there has not been pressure to make them generalizable or composable.
更糟糕的是，许多可解释性技术还没有完全应用到抽象中，因为没有这样一种压力存在从而使它们成为可推广的或可组合的。

Environment statistics frequently lack one or more of the standard attributes of high-quality statistics, namely, relevance, accuracy, timeliness, accessibility, interpretability and coherence.
环境统计经常缺乏高质量统计的一个或多个标准特性，即相关性、准确性、及时性、可获得性、可解释性和一致性。

Athiwaratkun& Wilson(2017)[27] extend this approach to a multimodal distribution that allows to deal with polysemy, entailment, uncertainty, and enhances interpretability.
Athiwaratkun&Wilson(2017)[25]将这种方法扩展成了一种多模态分布（multimodaldistribution），从而可以处理多义词、蕴涵、不确定性，以及提升可解释性。

The interpretability of statistical information reflects the availability of the supplementary information, referred to as metadata, necessary to interpret and utilize the information appropriately.
统计资料的可解读性所反映的是，是否能得到为了对资料作出适当的解读和利用而需要的补充资料(称为元数据)。

Interpretability is assisted by the presentation of metadata that is appropriate to the needs of a range of different users and uses of the data and is both well structured and readily accessible.
如元数据的列报与各不同用户的需求以及结构合理、随时可用的数据的用途相符合，对可解释性也有帮助。

In most cases, deep learning-based solutions lack mathematical elegance and offer very little interpretability of the found solution or understanding of the underlying phenomena.
在大多数情况下，基于深度学习而获得的解决方案，不但缺乏数学的优雅，而且会出现对已经发现的解决办法提供很少的解释性或对底层缺乏理解的现象。

(i) Interpretability;
(i)可解释性；.

The features will lose interpretability.
特征将失去可解释性.

It has comparatively low model interpretability.
它具有相对较低的模型可解释性。

By this view, interpretability seems essential.
这样,可解释性似乎是必不可少的。

Interpretability is one of the primary problems with machine learning.
可解释性是机器学习的主要问题之一。

Therefore, interpretability of the results is very important;
因此，结果的可解释性是非常重要的；.

In which stage of this process do you need interpretability?
在这个过程的哪个阶段需要可解释性?

Interpretability- the result of clustering should be comprehensive and usable.
可解释性-集群的结果应该是全面且可用的。

The belief that accuracy must be sacrificed for interpretability is inaccurate.
认为必须牺牲准确性来换取可解释性的观点是不正确的。

This is significant because, in some domains, interpretability is critical.
这很重要，因为在某些领域，可解释性非常重要。

This is important because in some domains, interpretability is quite important.
这是很重要的，因为在某些领域可解释性至关重要。

We are developing methods that allow better interpretability of machine learning systems.
我们正在开发方法，使机器学习系统具备更好的可解释性。

This is important because in some domains, interpretability is critical.
这很重要，因为在某些领域，可解释性非常重要。