So if you've ever picked out paint, you know that every infinitesimally different shade of blue, beige, and gray has its own descriptive, attractive name. Tuscan sunrise, blushing pear, Tradewind, etc… There are in fact people who invent these names for a living. But given that the human eye can see millions of distinct colors, sooner or later we're going to run out of good names. For this experiment, I gave the neural network a list of about 7,700 Sherwin-Williams paint colors along with their RGB values. One way I have of checking on the neural network's progress during training is to ask it to produce some output using the lowest-creativity setting.

Buying paint is always an enlightening affair. The names that companies come up with for their pigments are usually worth a chuckle or two, at least. Browsing through the color swatches, you're likely to stumble upon some curious choices, like a soft lilac color called Potentially Purple, a light blue known as Salty Tear, or maybe just a nondescript Gray Area. Even so, humans may no longer have a monopoly on the esoteric color-naming game. Janelle Shae, famous for using neural networks to come up with Death Metal band names like "Verk" or "Chaorug," or cake and cookie recipes featuring novel ingredients like horseradish and chicken, has programmed software to create new paint colors and give them names.

At some point, we've all wondered about the incredibly strange names for paint colors. Research scientist and neural network goofball Janelle Shane took the wondering a step further. Shane decided to train a neural network to generate new paint colors, complete with appropriate names. The results are possibly the greatest work of artificial intelligence I've seen to date. Writes Shane on her Tumblr, "For this experiment, I gave the neural network a list of about 7,700 Sherwin-Williams paint colors along with their RGB values. Could the neural network learn to invent new paint colors and give them attractive names?"