Watson, DS; (2021) No explanation without inference. In: AISB 2021 Symposium Proceedings: Overcoming Opacity in Machine Learning. (pp. pp. 9-11). Society for the Study of Artificial Intelligence & Simulation of Behaviour

Preview

Text Watson_AISB_2021.pdf - Accepted Version Download (214kB) | Preview

Abstract

Complex algorithms are increasingly used to automate high-stakes decisions in sensitive areas like healthcare and finance. However, the opacity of such models raises problems of intelligibility and trust. Researchers in interpretable machine learning (iML) have proposed a number of solutions, including local linear approximations, rule lists, and counterfactuals. I argue that all three methods share the same fundamental flaw – namely, a disregard for severe testing. Techniques for quantifying uncertainty and error are central to scientific explanation, yet iML has largely ignored this methodological imperative. I consider examples that illustrate the dangers of such negligence, with an emphasis on issues of scoping and confounding. Drawing on recent work in philosophy of science, I conclude that there can be no explanation – algorithmic or otherwise – without inference. I propose several ways to severely test existing iML methods and evaluate the resulting trade-offs.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item