"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:

Self-Cleaning Cars
Everything You Need for Testing DNA, In 1 Hour, in Less Than Half the Size of a Business Card
That Mobile Phones Are Phones is Besides the Point
Getting Away May Be Hard to Do: the Virtual Offices of 2025
NASA's Next Generation Space Engines Tested for 5 Years Straight