Explained: How to tell if artificial intelligence is working the way we want it to

Deep-learning models have become very powerful, but that has come at the expense of transparency. As these models are used more widely, a new area of research has risen that focuses on creating and testing explanation methods that may shed some light on the inner-workings of these black-box models.

Related Keywords

Yilun Zhou ,Marzyeh Ghassemi ,Artificial Intelligence Laboratory ,Healthy Ml Group ,Interactive Robotics Group Of The Computer Science ,Microsoft ,Interactive Robotics Group ,Computer Science ,Explainable Ai ,Nterpretability ,Deep Learning ,Black Box Models ,Eature Attribution Methods ,Explainable Artificial Intelligence ,