Psychometrics is the science of measurement of human intelligence, knowledge, aptitude and personality. By analogy, we need a science of computational psychometrics for measuring the intelligence and knowledge of intelligent machines. In psychometrics, the most common and reliable test of human intelligence is the Raven’s Progressive Matrices Test that relies solely on a set of visual analogy problems. By analogy, we propose understanding visual drawings as a test of machine intelligence. Understanding drawings requires background knowledge, commonsense reasoning, as well as mental imagery, all of which appear central to human-level intelligence.
Recent News
New Podcast on Jill Watson and SAMI
Hiring a full-time research scientist and a half-time post-doc
News coverage on Jill Watson: what different sectors can teach us about AI
Congratulations to DILab alumni Mukundan Kuthalam for his recent acceptance to the Computer Science PhD program at Northwestern University!
Congratulations to DILab alumni Varsha Achar for starting her new job at Facebook!