A group of researchers at the University Illinois (Chicago) have IQ-tested one of the best available artificial intelligence systems to see how smart the computer really is. Their results?
It’s about as smart as a four-year-old.
The team tested the ConceptNet 4, an artificial-intelligence system developed at M.I.T. by administering verbal portions of the Weschsler Preschool and Primary Scale of Intelligence Test, a standard IQ assessment for young children. While they found that the computer has the average IQ of a young child, unlike most children, the computer’s scores were very uneven across different parts of the test.
“If a child had scores that varied this much, it might be a symptom that something was wrong,” said Robert Sloan, professor and head of computer science at UIC, and lead author on the study. He added that ConceptNet 4 did very well on a test of vocabulary as well as on one that tested its abilities to recognize similarities. “But ConceptNet 4 did dramatically worse than average on comprehension—the ‘why’ questions,” Sloan said.
This is one of the hardest problems standing in the way of artificial intelligence nowadays: developing a program that can make sound judgment based on simple perception of the situation or facts; that is, commonsense.
“All of us know a huge number of things,” said Sloan. “As babies, we crawled around and yanked on things and learned that things fall. We yanked on other things and learned that dogs and cats don’t appreciate having their tails pulled.” Life is a rich learning environment.
“We’re still very far from programs with commonsense–AI that can answer comprehension questions with the skill of a child of 8,” said Sloan. He and his colleagues hope the study will help to focus attention on the “hard spots” in AI research.
The study was reported at the U.S. Artificial Intelligence Conference.
Story via: uic.edu
Advertisement
Learn more about Electronic Products Magazine
