News for hackers. Stuff that matters.

zz34

This is complete rubbish. Zero evaluation compared to any sane baseline, zero thinking about representation (predicting raw price?!). I'll just say it, ML was frankly better when fewer people knew it and there was less money in claiming to be an expert.
Welcome to ML in 2018.
When will you just admit the initial claim about ND4J being faster than Neanderthal was bogus?