News for hackers. Stuff that matters.
Re:Show HN: Neural network color recognition by kowdermeister on Monday March 09, 2015 @05:45AM (#9170047)
I don't get it. If you trained to recognize black and white, why did it find such a complex pattern where there were clearly none in the first example? Isn't it an example that it failed?
Re:Show HN: Neural network color recognition by ilzmastr on Monday March 09, 2015 @09:43AM (#9170821)
Interesting stuff, nice work!

The complex pattern is a result of the network doing the equivalent of fitting 3 gaussians (1 for each of RGB color channel) on the intensity of the pixel in that channel. I was curious, so I recorded a tiny demo of doing the equivalent piecewise in photoshop: http://cl.ly/183Z3w1V1B0F

Posterization in photoshop is a k-means technique, and each k-mean is a center of a gaussian, hence my motivation for the analogue video.

The triangles in the thresholded image make me think that the network is doing the equivalent of predicting a probability that a certain pixel is white/black per channel, and then these channels collude for the final decision, and thus we see triangles when the intersections of the 3 triangly spaced gaussians yield a value above some threshold.

Pic of the different channels: http://cl.ly/image/1w371V3U0N02

Re:Show HN: Neural network color recognition by megalodon on Monday March 09, 2015 @12:23PM (#9171841)
Great analysis, I hope you don't mind my linking to this comment as an explanation of the fractal patterns in the readme?
Re:Show HN: Neural network color recognition by megalodon on Monday March 09, 2015 @06:54AM (#9170232)
It sure is an interesting output, which is why I put it under 'observations'. For every color (24-bit binary) the network receives it has to output either black or white, which it does, so I wouldn't call it a failure.