How did the different models validate?

I have tried to figure out from the text — but beyond the evaluation of training the simple pendulum on several periods, I can not find any information on this: How did the results actually validate? How large were the errors? Could we get figures that compare the validation data with actual prediction from training runs?

…read more, vote or answer

Mikael Vejdemo-Johansson • 312

• 7 Jan 2016 3:04pm

waiting for moderation