Multi-disciplinary Use Cases for Convergent new Approaches to AI explainability

开发和测试方法，允许在透明度，可解释性和可解释性方面解释人工智能算法的预测，已成为当今人工智能领域最重要的开放问题之一。在这项提案中，我们汇集了来自不同领域的研究人员，他们具有互补的技能，对于能够理解AI算法的行为至关重要，这将通过一组有趣的多学科用例进行研究，其中可解释的AI可以发挥关键作用，并将用于量化优势，突出并可能解决不同应用背景下可用的可解释AI方法的弱点。到目前为止，阻碍可解释性取得实质性进展的一个方面是，在可解释人工智能中提出的几种解决方案在针对特定应用进行定制后被证明是有效的，并且通常不容易转移到其他领域。在这个项目中，我们将测试相同的一系列技术，用于解释故意选择的用例，这些用例在数据类型，学习任务和科学问题方面非常异构。拟议的用例范围从高能物理AI应用，到医学成像中的AI应用，到用于诊断肺部、气管和鼻气道疾病的AI应用，再到用于改善神经科学分析和建模的可解释性机器学习技术。对于每个用例，研究项目将包括三个阶段。在第一部分中，我们将应用最先进的可解释性技术，根据需求适当选择，以考虑的情况。在第二部分中，将确定这些技术的缺点。最值得注意的是，高维和原始数据的可扩展性问题，其中与感兴趣的信号相比，噪声可能很普遍，只要每个算法提供的可认证性水平，将被考虑在内。在最后阶段，将结合每个用例中构建的算法和知识，以记录结果，并开发通用程序和工程管道，用于在一般和不同领域利用xAI方法。

Developing and testing methodologies that allow to interpret the predictions of the AI algorithms in terms of transparency, interpretability, and explainability has become today one of the most important open questions in AI. In this proposal we bring together researchers from different fields with complementary skills, essential to be able to understand the behaviour of the AI algorithms, that will be studied with an interesting set of multidisciplinary use-cases in which explainable AI can play a crucial role and that will be used to quantify strengths and highlight, and possible solve, weaknesses of the available explainable AI methods in different applicative contexts. One aspect hindering so far substantial progress towards explainability is the fact that several proposed solutions in explainable AI proved to be effective after being tailored to specific applications, and frequently not easily transferred to other domains. In this project, we will test the same array of techniques for explainability to use-cases intentionally chosen to be quite heterogeneous with respect to the types of data, learning tasks, scientific questions. The proposed use-cases range from High Energy Physics AI applications, to applied AI in medical imaging, to AI applied for the diagnosis of pulmonary, tracheal and nasal airways diseases, to machine-learning techniques of explainability used to improve analysis and modelling in neuroscience. For each use-case, the research project will consist of three phases. In the first part, we will apply state-of-the-art explainability techniques, properly chosen based on the requirements, to the case under consideration. In the second part, shortcomings of the techniques will be identified. Most notably, issues of scalability to high-dimensional and raw data, where noise can be prevalent compared to the signal of interest, will be taken into consideration, as long as the level of certifiability afforded by each algorithm. In the final phase, algorithms and knowledge built in each use-case will be combined in order to document the results and to develop general procedures and engineering pipelines useful for the exploitation of xAI methods in general and different domains.