Providing high quality explanations for AI predictions based on machine learning is a challenging and complex task. To work well it requires, among other factors: selecting a proper level of generality/specificity of the explanation; considering assumptions about the familiarity of the explanation beneficiary with the AI task under consideration; referring to specific elements that have contributed to the decision; making use of additional knowledge (e.g. metadata) which might not be part of the prediction process; selecting appropriate examples; providing evidence supporting negative hypothesis. Finally, the system needs to formulate the explanation in a clearly interpretable, and possibly convincing, way.
Given these considerations, ANTIDOTE fosters an integrated vision of explainable AI, where low level characteristics of the deep learning process are combined with higher level schemas proper of the human argumentation capacity. The ANTIDOTE integrated vision is supported by three considerations: (i) in neural architectures the correlation between internal states of the network (e.g., weights assumed by single nodes) and the justification of the network classification outcome is not well studied; (ii) high quality explanations are crucially based on argumentation mechanisms (e.g., provide supporting examples and rejected alternatives), that are, to a large extent, task independent; (iii) in real settings, providing explanations is inherently an interactive process, where an explanatory dialogue takes place between the system and the user. Accordingly, ANTIDOTE will exploit cross disciplinary competences in three areas, i.e., deep learning, argumentation and interactivity, to support a broader and innovative view of explainable AI. Although we envision a general integrated approach to explainable AI, we will focus on a number of deep learning tasks in the medical domain, where the need for high quality explanations for clinical cases deliberation is critical.