The initial successes in recent years in harnessing machine learning technologies to improve medical practice and benefit patients have attracted attention in a wide range of healthcare fields. Particularly, it should be achieved by providing automated decision recommendations to the treating clinician. Some hopes placed in such ML-based systems for healthcare, however, seem to be unwarranted, at least partially because of their inherent lack of transparency, although their results seem convincing in accuracy and reliability. Skepticism arises when the physician as (...) the agent responsible for the implementation of diagnosis, therapy, and care is unable to access the generation of findings and recommendations. There is widespread agreement that, generally, a complete traceability is preferable to opaque recommendations; however, there are differences about addressing ML-based systems whose functioning seems to remain opaque to some degree—even if so-called explicable or interpretable systems gain increasing amounts of interest. This essay approaches the epistemic foundations of ML-generated information specifically and medical knowledge generally to advocate differentiations of decision-making situations in clinical contexts regarding their necessary depth of insight into the process of information generation. Empirically accurate or reliable outcomes are sufficient for some decision situations in healthcare, whereas other clinical decisions require extensive insight into ML-generated outcomes because of their inherently normative implications. (shrink)

In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project of offering a pragmatic and naturalistic account of understanding in AI. Intuitively, the purpose of providing an explanation of a model or a decision is to make it understandable to its stakeholders. But without a previous grasp of what it means to say that an agent understands a model or a decision, the explanatory strategies will (...) lack a well-defined goal. Aside from providing a clearer objective for XAI, focusing on understanding also allows us to relax the factivity condition on explanation, which is impossible to fulfill in many machine learning models, and to focus instead on the pragmatic conditions that determine the best fit between a model and the methods and devices deployed to understand it. After an examination of the different types of understanding discussed in the philosophical and psychological literature, I conclude that interpretative or approximation models not only provide the best way to achieve the objectual understanding of a machine learning model, but are also a necessary condition to achieve post hoc interpretability. This conclusion is partly based on the shortcomings of the purely functionalist approach to post hoc interpretability that seems to be predominant in most recent literature. (shrink)

Jotta olisimme moraalisesti vastuussa teoistamme, meidän on kyettävä muodostamaan käsityksiä oikeasta ja väärästä ja toimimaan ainakin jossain määrin niiden mukaisesti. Jos olemme täysivaltaisia moraalitoimijoita, myös ymmärrämme miksi jotkin teot ovat väärin, ja kykenemme siten joustavasti mukauttamaan toimintaamme eri tilanteisiin. Esitän, ettei näköpiirissä ole tekoälyjärjestelmiä, jotka kykenisivät aidosti välittämään oikein tekemisestä tai ymmärtämään moraalin vaatimuksia, koska nämä kyvyt vaativat kokemustietoisuutta ja kokonaisvaltaista arvostelukykyä. Emme siten voi sysätä koneille vastuuta teoistaan. Meidän on sen sijaan pyrittävä rakentamaan keinotekoisia oikeintekijöitä - järjestelmiä, jotka eivät (...) ole moraalitoimijoita, mutta kuitenkin toimivat likipitäen siten kuin me itse parhaimmillamme tekisimme. (shrink)

We argue that the robustness analysis of idealized models can have confirmational power. This responds to concerns recently raised in the literature, according to which the robustness analysis of models whose idealizations are not discharged is unable to confirm the causal mechanisms underlying these models, and the robustness analysis of models whose idealizations are discharged is unnecessary. In response, we make clear that, where idealizations sweep out, in a specific way, the space of possibilities— which is sometimes, though not always, (...) the case—they can be holistically discharged. In turn, this can be used to show that the robustness analysis of idealized models can have confirmational force after all. (shrink)