A.I. birdwatcher lets you see through the eyes of a machine

Link

This A.I. birdwatcher lets you ‘see’ through the eyes of a machine. Duke Today, October 31, 2019. It can take years of birdwatching experience to tell one species from the next. But using an artificial intelligence technique called deep learning, Duke University researchers have trained a computer to identify up to 200 species of birds from just a photo. This tool goes beyond giving the right answer to explain its thinking in a way that even someone who doesn’t know a penguin from a puffin can understand. Picked up by BBC Digital Planet and MIT Technology Review.

Birds perceive ‘warm’ colors differently from ‘cool’ ones

Link

Birds perceive ‘warm’ colors differently from ‘cool’ ones. Duke Today, May 29, 2019. Birds may not have a word for maroon. Or burnt sienna. But show a zebra finch a sunset-colored object, and she’ll quickly decide whether it looks more “red” or “orange.” A new study shows that birds mentally sort the range of hues on the blue-green side of the spectrum into two categories too, but the line between them is fuzzier, perhaps because “either/or” thinking is less useful in this part of the spectrum, researchers say.