Several weeks ago, artist and coder Janelle Shane tried to train a neural network to name paint colours. The results were...not good. "Stanky Bean" was a kind of dull pink, and "Stoner Blue" was grey. Then there were the three shades of brown known as "Dope," "Burble Simp," and "Turdly."
These results were so bad that they turned the corner into delightful hilarity, and Shane's blog post about them went viral. Almost immediately, AI coders started offering tips on how she could tweak the algorithm to get better results.
First, Shane realised that part of the initial problem was that she'd cranked up the neural net's "temperature" variable, which meant that it was picking less likely (or "more creative") possibilities as it generated paint names letter-by-letter. So she turned the temperature variable down and found that the names were still pretty silly but they at least matched the colours most of the time. Plus, the colours themselves seemed more varied. The problem is, according to Shane, that RGB doesn't do a good job representing colour the way human eyes perceive it.
To read full article - https://goo.gl/buPQXb