We argue that artificial networks are explainable and offer a novel theory of interpretability. Two sets of conceptual questions are prominent in theoretical engagements with artificial neural networks, especially in the context of medical artificial intelligence: Are networks explainable, and if so, what does it mean to explain the output of a network? And what does it mean for a network to be interpretable? We argue that accounts of “explanation” tailored specifically to neural networks have ineffectively reinvented the wheel. In (...) response to, we show how four familiar accounts of explanation apply to neural networks as they would to any scientific phenomenon. We diagnose the confusion about explaining neural networks within the machine learning literature as an equivocation on “explainability,” “understandability” and “interpretability.” To remedy this, we distinguish between these notions, and answer by offering a theory and typology of interpretation in machine learning. Interpretation is something one does to an explanation with the aim of producing another, more understandable, explanation. As with explanation, there are various concepts and methods involved in interpretation: Total or Partial, Global or Local, and Approximative or Isomorphic. Our account of “interpretability” is consistent with uses in the machine learning literature, in keeping with the philosophy of explanation and understanding, and pays special attention to medical artificial intelligence systems. (shrink)

In a recent reply to our article, “What is Interpretability?,” Prasetya argues against our position that artificial neural networks are explainable. It is claimed that our indefeasibility thesis—that adding complexity to an explanation of a phenomenon does not make the phenomenon any less explainable—is false. More precisely, Prasetya argues that unificationist explanations are defeasible to increasing complexity, and thus, we may not be able to provide such explanations of highly complex AI models. The reply highlights an important lacuna in our (...) original paper, the omission of the unificationist account of explanation, and affords us the opportunity to respond. Here, we argue that artificial neural networks are explainable in a way that should satisfy unificationists and that interpretability methods present ways in which ML theories can achieve unification. (shrink)

Inferences from clinical research results to estimates of therapeutic effectiveness suffer due to various biases. I argue that predictions of medical effectiveness are prone to failure because current medical research overlooks the impacts of a particularly detrimental set of biases: meta-biases. Meta-biases are linked to higher-level characteristics of medical research and their effects are only observed when comparing sets of studies that share certain meta-level properties. I offer a model for correcting research results based on meta-research evidence, the bias dynamics (...) model, which employs regularly updated empirical bias coefficients to attenuate estimates of therapeutic effectiveness. (shrink)