A widespread need to explain the behavior and outcomes of AI-based systems has emerged, due to their ubiquitous presence. Thus, providing renewed momentum to the relatively new research area of eXplainable AI (XAI). Nowadays, the importance of XAI lies in the fact that the increasing control transference to this kind of system for decision making -or, at least, its use for assisting executive stakeholders- already affects many sensitive realms (as in Politics, Social Sciences, or Law). The decision-making power handover to (...) opaque AI systems makes mandatory explaining those, primarily in application scenarios where the stakeholders are unaware of both the high technology applied and the basic principles governing the technological solutions. The issue should not be reduced to a merely technical problem; the explainer would be compelled to transmit richer knowledge about the system (including its role within the informational ecosystem where he/she works). To achieve such an aim, the explainer could exploit, if necessary, practices from other scientific and humanistic areas. The first aim of the paper is to emphasize and justify the need for a multidisciplinary approach that is beneficiated from part of the scientific and philosophical corpus on Explaining, underscoring the particular nuances of the issue within the field of Data Science. The second objective is to develop some arguments justifying the authors’ bet by a more relevant role of ideas inspired by, on the one hand, formal techniques from Knowledge Representation and Reasoning, and on the other hand, the modeling of human reasoning when facing the explanation. This way, explaining modeling practices would seek a sound balance between the pure technical justification and the explainer-explainee agreement. (shrink)

Decision-making has traditionally been modelled as a serial process, consisting of a number of distinct stages. The traditional account assumes that an agent first acquires the necessary perceptual evidence, by constructing a detailed inner repre- sentation of the environment, in order to deliberate over a set of possible options. Next, the agent considers her goals and beliefs, and subsequently commits to the best possible course of action. This process then repeats once the agent has learned from the consequences of her (...) actions and subsequently updated her beliefs. Under this interpretation, the agent’s body is considered merely as a means to report the decision, or to acquire the relevant goods. However, embodied cognition argues that an agent’s body should be understood as a proper part of the decision-making pro- cess. Accepting this principle challenges a number of commonly held beliefs in the cognitive sciences, but may lead to a more unified account of decision-making. This thesis explores an embodied account of decision-making using a recent frame- work known as predictive processing. This framework has been proposed by some as a functional description of neural activity. However, if it is approached from an embodied perspective, it can also offer a novel account of decision-making that ex- tends the scope of our explanatory considerations out beyond the brain and the body. We explore work in the cognitive sciences that supports this view, and argue that decision theory can benefit from adopting an embodied and predictive perspective. (shrink)