Screenshot\/HomestarRunner.com <\/p>\n
Humans arent nearly as creative as we think. Craft brewers, for example, have run out of fun names and are sending each other cease and desist letters for coming up with the same ideas. So, what if we let computers come up with new names for us?<\/p>\n
Thats the problem optics industry research scientist Janelle Shane has been trying to solve using neural networks, but with paint colors. The initial results are downright ridiculous. Like Stanky Bean and Sindis Poop. <\/p>\n
By problem, I actually mean she was just trying to have a good time online. What inspired me was I found a post online from someone whod done neural network cookbook recipes, she told Gizmodo. I thought they were hilarious and I wanted more, but there werent any more. The only way to get more was to make more. <\/p>\n
Neural networks are essentially computer systemsthat can be trained on large datasets to solve problems like speech or pattern recognition. Shane analyzed a list of 7700 paint colors from Sherwin Williams with a neural network called char-rnn, including both the paint names and their red, blue, and green values. <\/p>\n
Once a neural network is trained, it can learn to find the next logical thing based on an input, which is how we ended up with those strange dog pictures last year. In this case, the neural network starts with a letter, then picks the next most logical letter (or a letter further down on the list, depending on the creativity setting) to create pronounceable words. Its like a child learning to speak if its parents only spoke about paint colors. <\/p>\n
Shane had the network spit out names during checkpoints as it was learning, at varying levels of creativity. Naturally, its most creative setting eventually started spitting out gibberish: <\/p>\n
(I am having trouble breathing from how hard I am laughing right now.)<\/p>\n
But eventually, it learned to make some really wacky paint names. <\/p>\n
Im sure Hurky wasnt in the original dataset, said Shane. But somehow its come up with that. <\/p>\n
Shane previously trained a neural network to come up with new recipe names, creating some of the funniest combinations of words imaginable. <\/p>\n
Its tempting to correct the spelling if it almost spells a word, but somehow that takes the fun out of it, said Shane. This is as it comes out of the computer, Im not changing a thing. <\/p>\n
Shanes just doing this for fun, but heres the link to char-rnn if youve got your own ideas. <\/p>\n
[Postcards from the Frontiers of Science] <\/p>\n
<\/p>\n
Read the original here: <\/p>\n
The First AI-Generated Paint Names Include 'Homestar Brown' and 'Stanky Bean' - Gizmodo<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Screenshot\/HomestarRunner.com Humans arent nearly as creative as we think. Continue reading