A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence
A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence
复制标题
DOI：
10.1109/tai.2024.3351798
复制
发表时间：
2024-01
期刊：
影响因子：
--
通讯作者：
Justus Renkhoff;Ke Feng;Marc Meier-Doernberg;Alvaro Velasquez;Houbing Herbert Song
中科院分区：
文献类型：
--
作者：
Justus Renkhoff;Ke Feng;Marc Meier-Doernberg;Alvaro Velasquez;Houbing Herbert Song
Neurosymbolic人工智能（AI）是AI的新兴分支，结合了符号AI和亚符号AI的优势。亚符号AI的主要缺点是它充当“黑匣子”，这意味着很难解释预测，从而使测试（T＆E）和验证（V＆V）过程的系统使用了亚符号AI挑战。由于Neurosymbolic AI结合了符号和亚符号AI的优势，因此该调查探讨了神经符号应用如何减轻V＆V过程。这项调查考虑了神经符号AI的两种分类法，评估它们，并分析了这些算法通常用作当前应用中的符号和亚符号成分。此外，还提供了这些组件的T＆E和V＆V流程的当前技术的概述。此外，还研究了符号部分如何用于当前神经符号应用中的T＆E和V＆V目的。我们的研究表明，通过利用符号AI的可能性来缓解亚符号AI的T＆E和V＆V过程的巨大潜力。此外，评估当前T＆E和V＆V方法对神经肯定AI的适用性，以及如何探索不同的神经偶然架构影响这些方法。发现当前的T＆E和V＆V技术部分足以进行测试，评估，验证或验证神经质质应用的符号和亚符号的部分，而其中一些方法则使用当前T＆E和V＆V方法的方法，默认情况下不适用，并且需要进行调整，甚至需要新的方法。我们的研究表明，使用符号AI来测试，评估，验证或验证亚符号模型的预测具有很大的潜力，从而使神经成像AI成为安全，安全和可信赖的AI的有趣研究方向。
Neurosymbolic artificial intelligence (AI) is an emerging branch of AI that combines the strengths of symbolic AI and sub-symbolic AI. A major drawback of sub-symbolic AI is that it acts as a"black box", meaning that predictions are difficult to explain, making the testing (T&E) and validation (V&V) processes of a system that uses sub-symbolic AI a challenge. Since neurosymbolic AI combines the advantages of both symbolic and sub-symbolic AI, this survey explores how neurosymbolic applications can ease the V&V process. This survey considers two taxonomies of neurosymbolic AI, evaluates them, and analyzes which algorithms are commonly used as the symbolic and sub-symbolic components in current applications. Additionally, an overview of current techniques for the T&E and V&V processes of these components is provided. Furthermore, it is investigated how the symbolic part is used for T&E and V&V purposes in current neurosymbolic applications. Our research shows that neurosymbolic AI as great potential to ease the T&E and V&V processes of sub-symbolic AI by leveraging the possibilities of symbolic AI. Additionally, the applicability of current T&E and V&V methods to neurosymbolic AI is assessed, and how different neurosymbolic architectures can impact these methods is explored. It is found that current T&E and V&V techniques are partly sufficient to test, evaluate, verify, or validate the symbolic and sub-symbolic part of neurosymbolic applications independently, while some of them use approaches where current T&E and V&V methods are not applicable by default, and adjustments or even new approaches are needed. Our research shows that there is great potential in using symbolic AI to test, evaluate, verify, or validate the predictions of a sub-symbolic model, making neurosymbolic AI an interesting research direction for safe, secure, and trustworthy AI.