[alpaca128]

It showed that machine learning is useless if the input format doesn't match the problem. The result would probably be better if the problem was approached more on a vector graphics-based level rather than throwing a bunch of pixel clusters at the program and expecting it to figure out the underlying shapes by itself.

I mean, children in school don't learn to write by copying printed letters out of a book either, instead they're shown the individual strokes and their direction step by step.

[miloignis]

His first attempt was vector based, the blobs of pixels / signed distance fields were his second attempt that worked better.