ITWORLD - Sep 15 - A Canadian researcher, Harm de Vries took 10K photos from Tinder and gave the computer his opinion on 8K of them. The computer tried to determine his likes or dislikes for the remaining images but managed only a 55% success rate. He decided the computer needed more images to choose from, so he pulled ~500K photos from OkCupid. With a greater number of images to work with, the computer achieved a 68% success rate. "It's a pretty good start," he said, "but I think it can be improved a lot."