Artificial neural networks. - page 10
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
Neural networks are IMHO the hardest part of algorithmic trading. There are no newbies here. I, too, only after 8 years of forex, having spent a lot of money, having tried all possible strategies and indicators and all possible combinations of them, decided that this is the only trading strategy that I haven't touched. Why have I not tried it before? I thought it was too complicated and required special programs like "neurosolutions". The most important thing is to understand how neural networks work, and the rest is a technical matter.
I invented my first prototype neuronet in about a day, wrote it in 15 minutes using pure MQL5, trained it using optimization. And oh my miracle, the results are encouraging... tank robustness is present for several years, tank tests are stable. Now I'm almost sure that if the Grail exists, it is hidden somewhere in the depths of neural networks: their potential is almost unlimited, I can add there any number of indicators with any number of parameters... and it can be done using pure MQL5. After thinking and trying them, all my previous efforts to create an Expert Advisor out of standard indicators appear to be child's play.
In this thread I propose to share my experience in the field of neural networks. It would be interesting to learn the principles of designing and training networks in MQL5. I am waiting for your comments.
Anyway, I repeatedly asked respected neural networker Mr. Reshetov, how is his R-Net #X doing? (Not in private, but in general topics, there is reason to suspect that he saw my question)...
Not a word in reply.
And JOO, as-is not too verbose on this bidding option ....
There I know the basis lies in the correctness of input data (which data? and its preparation...) to the networks...
At one time I tried to use FANN bible on mcl4... More or less understood it...
I myself will return to this topic in full after the development and testing of exposures based on mcl5, mcl4 spread trading.
By the way, interested - real-time trading!
...
How is your R-Net X doing? Yield graph, reports, etc.
Now looking at your GoldDust. Maybe you have something to say on the subject and recommend how to use it in real trading.
No response on the mcl4 forum....
Spc.
Anyway, Mr Reshetov, an honoured neuro-networker, has been asked repeatedly how his R-Net #X is doing?
Leaking, how else could it be.
And anyway, what difference would it make if someone showed something? The examples of Better and Leov are not enough to kick your ass? Then we can just score )
He's a loser, how else could he be?
And anyway, what difference would it make if someone showed something? The examples of Batter and Leova are not enough to kick your ass? Then we can just score )
I just used to trade R-Net - on real on mcl4 - didn't lose (went into a drawdown and came out of it safely... trades on the daily). I can post reports... With the same settings to the present time ...
About Leov (LeoV) example, can you elaborate a bit more...
An example, Bötter - on his profile... :-)
By the way, here's a Bettor for you... :-)
And JOO doesn't seem to be too verbose about this bidding option...
What can I say...
I have a system, very promising, traded in plbues, but gradually begin to increase over time drawdowns (before the new training). My nerves are failing me and I start to close unprofitable positions. I don't know how to deal with it (with drawdowns and nerves that gradually increase).
In short - the topic of neural networks is very interesting and promising, no matter what anyone says, but it requires a tremendous amount of time to study. Temporarily abandoned (until I have some free time to study them).
1. What can I say...
I have a system, very promising, traded in plbues, but gradually the drawdowns start to increase over time (before new training). My nerves are failing me and I start to cover loss-making positions. I do not know how to deal with it (with gradually increasing drawdowns and nerves).
2. In short - the topic of neural networks is very interesting and promising, no matter what anyone says, but it requires a tremendous amount of time to study. Temporarily abandoned (until I have some free time to study them).
1. Thanks for the comment!
As soon as I'll be at R-Neta's - I'll launch to the present... I also seem to have jumped out of it in time on the real one (as I came out of the drawdown)... :-)
2. OK! Get hooked on spread trading automation and parallel with your Ilans! Here's the situation from micro - real...
Preparing the ground... :-)
Such a study costs money with an uncertain result. In addition, MQL5 (as well as C/C++) are not suitable for full-fledged research.
Such a study costs money with an uncertain result. Besides, MQL5 (as well as C/C++) are not suitable for full-fledged research.
What programming languages are suitable?
Please, write it down slowly, so I can write it down in my notebook.
Seen attempts in neighbouring threads to "teach" the network the multiplication table - can't stand up to scrutiny
To take the championship as an example: right now the leader is JPAlonso with a score of 56713, my neural network "says" that his maximum will not exceed 63000 and he is close to flush