Mistaking a teapot shape for a golf ball, due to surface features, is one striking example from a recent open-access paper:
The networks did “a poor job of identifying such items as a butterfly, an airplane and a banana,” according to the researchers. The explanation they propose is that “Humans see the entire object, while the artificial intelligence networks identify fragments of the object.” News, “Researchers: Deep Learning vision is very different from human vision” at Mind Matters
“To see life steadily and see it whole”* doesn’t seem to be popular among machines.
*(Zen via Matthew Arnold)
See also: Can an algorithm be racist?