Even smartest AI can't match human eye - Gadget

A common artificial intelligence model known as deep convolutional neural networks (DCNNs) does not see objects the way humans do – and that could be dangerous in real-world AI applications. That is the conclusion of Professor James Elder, co-author of a York University study published recently, which finds that AI cannot use something called "configural shape perception", which is standard in human perception for recognising shapes. Published in the Cell Press journal iScience, the paper Deep learning models fail to capture the configural nature of human shape perception is a collaborative study by Elder, who holds the York research chair in human and computer vision and is co-director of York's Centre for AI & Society, co-authored with assistant psychology professor Nicholas Baker at Loyola College in Chicago, a former postdoctoral fellow at York. The study employed novel visual stimuli called "Frankensteins" to explore how the human brain and DCNNs process holistic, configural object properties. "Frankensteins are simply objects that have been taken apart and put back together the wrong way around," says Elder. "As a result, they have all the right local features, but in the wrong places."