Drexel University

College of Computing and Informatics

EXPLAINABLE AI

Bridge the gap between humans and AI by comparing, and contrasting the ability of eXplainable AI methods to explain neural nets.
Problem: Complex AI systems are hard to be interpreted by human users 
Consequences of the problem: accountability, transparency, and ethics
Fact: no ground truth models are being used to guide the scientific advance of XAI
...
...

Team Members

...
...
...