Artificial intelligence passed the basic Turing test of penmanship and can recognize handwritten drawings after viewing the figures a few times.
Turing Test is an experiment designed by Alan Turing, a British computer scientist and called the father of modern computer science, to compare an artificial intelligence's ability to think like human.
"The use of words and general educated opinion will have altered so much that one will be able to speak of machines thinking without expecting to be contradicted," Dr Turing had once predicted.
Unlike people in the test who could not tell the difference between figures drawn by computer or human, the computer program's performance was consistent according to The Christian Science Monitor.
"In the current AI landscape, there's been a lot of focus on classifying patterns. But what's been lost is that intelligence isn't just about classifying or recognizing; it's about thinking," Joshua Tenenbaum, study co-author and a professor in the Department of Brain and Cognitive Sciences at the Massachusetts Institute of Technology, said in a report by Tech Times.
Researchers used 50 handwritten languages such as Glagolitic, Gujarati, Sanskrit and Tibetan to test the computer program called "Bayesian Program Learning Framework." The program demonstrated that the program could sometimes perform even better than humans.
"For the first time, we think we have a machine system that can learn a large class of visual concepts in ways that are hard to distinguish from human learners," Tenenbaum said.
As part of the test, humans and the artificial intelligence were shown an image once and asked to pick same image from a set of 20.
The computer program beat the humans with an error rate of 3.3 percent, while humans performed at 4.5 per cent.
Science Mag detailed the visual Turing test of an artificial intelligence program, titled "Human-Level Concept Learning Through Probabilistic Program Induction."
