Computers can already hold a massive amount of instantly-retrievable data in a manner that puts most humans to shame, but getting them to actually display intelligence is an entirely different challenge. A team of researchers from Northwestern University just made a huge stride towards that goal with a computational model that actually outperforms the average American adult in a standard intelligence test.
As PhysOrg reports, the witty computer system utilizes an AI platform called CogSketch that gives it the power to solve visual problems just by looking at them, which is something that has traditionally held back many examples of artificial intelligence. Being able to visually understand, interpret, and then use that data to come to a solution brings the computer system closer to the functioning of the human brain than many before it, and so the team pitted its creation against a popular standardized test called Raven’s Progressive Matrices.
The Raven’s test (or RPM for short) is comprised of 60 multiple choice questions that measure the taker’s ability to reason, using visual puzzles. For each question a series of shapes is given and the test subject must identify the pattern and select whichever shape should logically come next.
The researcher’s AI system performed extremely well on the test, placing in the 75th percentile of American adults. What’s more, the places where the AI stumbled are also spots where human test takers have gotten stuck.
“Most artificial intelligence research today concerning vision focuses on recognition, or labeling what is in a scene rather than reasoning about it,” Northwestern’s Ken Forbus said. “But recognition is only useful if it supports subsequent reasoning. Our research provides an important step toward understanding visual reasoning more broadly.” Basically, the day when computers enslave humanity is just around the corner.
