Mar 12, 2019
Unmasking Clever Hans predictors and assessing what machines really learn
Posted by Caycee Dee Neely in categories: entertainment, robotics/AI
Is your AI intelligent or just looking like it’s intelligent? In many ways, this depends on your idea of AI and what it is supposed to do. Scientists at Singapore University of Technology and Design have worked out a way to check for the issue. Open Access Journal: https://www.nature.com/articles/s41467-019-08987-4
Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly intelligent behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showcases a spectrum of problem-solving behaviors ranging from naive and short-sighted, to well-informed and strategic. We observe that standard performance evaluation metrics can be oblivious to distinguishing these diverse problem solving behaviors. Furthermore, we propose our semi-automated Spectral Relevance Analysis that provides a practically effective way of characterizing and validating the behavior of nonlinear learning machines. This helps to assess whether a learned model indeed delivers reliably for the problem that it was conceived for. Furthermore, our work intends to add a voice of caution to the ongoing excitement about machine intelligence and pledges to evaluate and judge some of these recent successes in a more nuanced manner.