[Talks@IDSIA] [Lumi] Talk on "How values encroach on understanding from opaque machine learning models" by Emily Sullivan (Eindhoven University of Technology) [Thursday, June 10, 2021, at 17:00 (5pm) CET, on Zoom]

We are happy to announce the fourth talk of the series of webinars at IDSIA dedicated to the foundational, epistemological and ethical aspects of AI. ******* *Title: How values encroach on understanding from opaque machine learning models *Abstract: How much is model opacity a problem for explanation and understanding from machine learning models? I argue that there are several ways in which non-epistemic values influence the extent to which model opacity undermines explanation and understanding. I consider three stages of the scientific process surrounding ML models where the influence of non-epistemic values emerges: 1) establishing the empirical link between the model and phenomenon, 2) explanation, and 3) attributions of understanding. *Speaker: Emily Sullivan, Assistant Professor of Philosophy & Ethics, Department of Industrial Engineering & Innovation Sciences, Eindhoven University of Technology (personal webpage: http://www.eesullivan.com) *Date: Thursday, June 10, 2021, at 17:00 (5pm) CET, on Zoom. *Zoom Link: https://supsi.zoom.us/j/62374021896?pwd=WWNIKy9MVm9DNThHeHBpazdBS1YzQT09 ID meeting: 623 7402 1896 Passcode: emily