zz34
Greenlight: Composable Integration Testing in Clojure
Re:Using a Keras Long Short-Term Memory Model to Predict Stock Prices
on Friday November 09, 2018 @01:45PM (#18416772)
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.
Re:Using a Keras Long Short-Term Memory Model to Predict Stock Prices
on Friday November 09, 2018 @01:43PM (#18416757)
Welcome to ML in 2018.
Re:Neanderthal vs. ND4J – Native Performance, Java and CPU
on Saturday June 23, 2018 @09:18AM (#17381138)
When will you just admit the initial claim about ND4J being faster than Neanderthal was bogus?