Algorithmic ''centrifuge'' - page 23
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Strategy generators, neural networks and other analogues (roughly) would make sense if there was some kind of fitness function to teach it all, guaranteeing the robustness of the system in the future. I don't know of such, imho they don't exist))) All sorts of test sampling is the same fit.
And without it, this whole centrifuge will throw its inhabitants out into the surrounding wilderness)))))))))
Neural networkers, by the way... Of course they know all this)))) When training a network, randomly disconnect neurons from the loop. Seems to make things more relevant, doesn't it? Has anyone tried it?
Strategy generators, neural networks and other analogues (roughly) would make sense if there was some kind of fitness function to teach it all, guaranteeing the robustness of the system in the future. I don't know of such, imho they don't exist))) All sorts of test sampling is the same fit.
And without it, this whole centrifuge will throw its inhabitants out into the surrounding wilderness)))))))))
Neural networkers, by the way... Of course they know all this)))) When training a network, randomly disconnect neurons from the loop. Seems to make things more relevant, doesn't it? Has anyone tried it?
There are such functions! Roll them up yourself!
A trivial example - split a sample of three months into three monthly sections andeee.
Your fitness function is the minimum difference of some calculation on all three. And if the forward is already minimally divergent - bingo!)
Happy New Year!
pyspas - there is such experience both in forward and trading.