Sign In

Communications of the ACM

ACM Opinion

Teaching AIs to Make Mistakes Like Kids Would Help Them Learn Faster

View as: Print Mobile App Share:
child and dog in stroller

Young children find it hard to understand that a poodle is also a dog.

Teaching artificial intelligence to think like children may make them better learners. Kanishk Gandhi and Brenden Lake at New York University found that a common assumption children make while learning, called the mutual exclusivity bias, would make AIs better at learning tasks such as processing language.

Mutual exclusivity bias refers to the incorrect assumption that once an object has a name or a label, it can't also have another.

From New Scientist
View Full Article – May Require Paid Subscription


No entries found