What to feed to the input of the neural network? Your ideas... - page 26
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
Just three entrances
in[1] = Close[1] - Close[2];
in[2] = Close[2] - Close[3];
in[3] = Close[3] - Close[4];
Scale optimisation for 2021
Forward almost 2 years: from 2022 to 2023-10-29
What's the catch. - It's one of hundreds or one of thousands of sets. You'll never find it amongst the flush sets.
What's the good news? - Neuronics can work on any data, as long as it reflects a little bit of what's happening on the chart
According to the formula, it was on such a signal that I entered the forum for the first time.
It's like ein, zwei, drei, and ......
I thought it wasn't working anymore.
No, it's working ;)
Make a signal on the demo, let's check it out ;)
I'll be pleasantly surprised if at least one neuron will make an iron profit.Judging by the formula, it was on such a signal that I first entered the forecourt.
Like ein, zwei, drei, and ......
I thought it wasn't working anymore.
No, it's working ;)
Make a signal on the demo, let's check it out ;)
OBS signal - if high-low is more than the limit, then trade towards open-close :-))
(trend OBS - "one grandmother said", if buckwheat becomes more expensive, you should buy buckwheat...).
PS/ the trouble with neural networks and MO is that their results cannot be interpreted (by improving your own neural network), but only tested in practice.
On the go a bunch of indicators, on the output =
On the go a bunch of indicators, on the output =
If that's the case, you don't have a very good bottom line.
I promised to leave the topic, but at the end of the day I'll give you another hint: to train neural network, you need your own tester, which would produce results not by closing, but by opening a deal. I.e. neural network, at the moment of opening a deal, should have information on the statistical probability of closing the opened deal in plus. Now, this is the last post in this thread(said too much already).
A lot for those who think.
Here, if the idea was for dummies, it would be great: what to do with prices, how to link them to this probability, how to calculate stops and takeouts, etc.
I promised to leave the topic, but at the end of the day I'll give you another hint: to train neural network, you need your own tester, which would produce results not by closing, but by opening a deal. I.e. neural network, at the moment of opening a deal, should have information on the statistical probability of closing the opened deal in plus. Now, this is the last post in this thread (already said too much).
Well ... all the secrets of the indicator ))))
https://www.mql5.com/ru/code/903
I promised to leave the topic, but at the end of the day I'll give you another hint: to train neural network, you need your own tester, which would produce results not by closing, but by opening a deal. I.e. neural network, at the moment of opening a deal, must have information on the statistical probability of closing the opened deal in plus. Now, this is the last post in this thread (already said too much).
After reading your post, caused me to grimace-smile "need your own t ester"
Sorry, Sergey, but a self-written tester, even the best in the world, can only chew historical data, but it does not know the future, no matter how much you want to present it here for novelty.
After each new tick you need a new self-written tester.))
You need a super computer
this neural network is broken, bring the next one....
You need a super computer