Our current machine learning (ML) models achieve impressive performance on many benchmark tasks. Yet, these models remain remarkably brittle, susceptible to manipulation and, more broadly, often behave in ways that are unpredictable to users. Why is this the case? In this talk by Aleksander Madry, Professor of Computer Science, Massachusetts Institute of Technology, we identify human-ML misalignment as a chief cause of this behavior. We then take an end-to-end look at the current ML training paradigm and pinpoint some of the roots of this misalignment. We discuss how current pipelines for dataset creation, model training, and system evaluation give rise to unintuitive behavior and widespread vulnerability. Finally, we conclude by outlining possible approaches towards alleviating these deficiencies.
This talk is provided as part of the C3 Digital Transformation Institute colloquium series on digital transformation science.
Sign up for the free insideAI News newsletter.
Join us on Twitter: @InsideBigData1 – https://twitter.com/InsideBigData1