Training AI not to misbehave

05 Dec 2019 03:58 17
4,304
Stanford Download
117 14

As robots, self-driving cars and other intelligent machines weave AI into everyday life, a new way of designing algorithms can help machine-learning developers build in safeguards against specific, undesirable outcomes like racial and gender bias, to help earn societal trust. Credit to Deboki Chakravarti.

Related of "Training AI not to misbehave" Videos