Changing How Computers Learn

Computer Learns Like a Human and (Sort Of) Beat the Turing Test

Lance Ulanoff | December 11, 2015

There is a fundamental difference between the way computers learn and the way humans learn. Humans can see one example and intuit what that object or symbol might be used for and quickly identify similar things. A computer can only arrive at the same conclusions after being fed thousands and thousands of examples. This usually referred to as "machine learning."
That may, however, be about to change.
Scientists at New York University have figured out a way to not only mimic how humans make those mental leaps, but to have computers recreate simple symbols and drawings in such a way that they're almost indistinguishable from these created by humans.

Source: https://plus.maths.org/issue5/turing/cartoon.gif

<more at http://mashable.com/2015/12/11/learning-computer-beats-turing-test/#e4_621xJSqqw; related links: http://www.aaas.org/news/researchers-bring-machine-learning-closer-human-performance (Researchers Bring Machine Learning Closer to Human-Like Performance. Researchers have introduced a computer model that learns a new concept much like humans do, from a single or very few examples. December 10, 2015) and http://www.eteknix.com/bayesian-program-learning-teaching-a-computer-in-one-shot/>