"He believes that the way his toddler learns and reasons may hold the key to making machines much more intelligent."

Using children as a model of how AIs should learn


Sun, Dec 20th, 2015 11:00 by capnasty NEWS

Albeit current deep-learning methodology has produced "some astonishing results," Gary Marcus, professor of psychology at New York University, thinks that in order to create a sophisticated machine capable of learning by extrapolating and generalizing, can be obtained by observing how children master the world around them.

[...] Among other things, he points out that these systems need to be fed many thousands of examples in order to learn something. Researchers who are trying to develop machines capable of conversing naturally with people are doing it by giving their systems countless transcripts of previous conversations. This might well produce something capable of simple conversation, but cognitive science suggests it is not how the human mind acquires language.

In contrast, a two-year-old’s ability to learn by extrapolating and generalizing—albeit imperfectly—is far more sophisticated. Clearly the brain is capable of more than just recognizing patterns in large amounts of data: it has a way to acquire deeper abstractions from relatively little data. Giving machines even a basic ability to learn such abstractions quickly would be an important achievement. [...]



You may also be interested in:

Playlist Player
Billiards in space
By the Time A.I.s Are Smart Enough, Humans Will be Even Smarter
Space Exploration Will Be Quite Unlike Anything Seen Before
What's Mine is Yours: The Rise of Collaborative Consumption