Communications of the ACM
ACM Opinion
Teaching AIs to Make Mistakes Like Kids Would Help Them Learn Faster
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