1. What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
    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 (...)
    Direct download (3 more)  
    Export citation  
    Bookmark   16 citations  
  2. Interpretability and Unification.Adrian Erasmus & Tyler D. P. Brunet - 2022 - Philosophy and Technology 35 (2):1-6.
    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 (...)
    No categories
    Direct download (4 more)  
    Export citation  
    Bookmark   2 citations  
  3.  9
    The Bias Dynamics Model: Correcting for Meta-biases in Therapeutic Prediction.Adrian Erasmus - forthcoming - Philosophy of Science:1-13.
    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 (...)
    Direct download (2 more)  
    Export citation  
    Bookmark   1 citation