"New Neural" is an Open Source neural network engine project for the MetaTrader 5 platform. - page 26
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
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
Victor, any help is welcome.
... I mean, you don't have to invent it, it needs to be implemented in MQL.
MQL5 C++ similar language, developers did a great job porting from C++ takes as little time as possible, C++ has a lot of neural network implementations, so there are plenty of scooters.
It's the starship that needs to be planned. Otherwise why bother with it? (rhetorical question)
....
It's the starship that needs to be planned. Otherwise, what's the point of doing it? (rhetorical question)
I agree 100%. There are tons and tons of scooters online. Why make another scooter?
There is a powerful platform for traders. There is a wonderful application language MQL5. And there is a great opportunity to make the MT5 platform the most powerful tool ever created. MT5 developers are well aware of that and haven't taken advantage of this opportunity, and that's why the neuro-engine project was initiated.
MQL5 C++ is a similar language, the developers did a great job to porting from C++ takes as little time as possible, there are a lot of implementations of neural networks in C++, so there are plenty of scooters.
It is the starship that needs to be planned. Otherwise, what's the point of doing it all? (rhetorical question)
Yes I agree that in the end it is desirable to have a starship, but from the beginning you need to get a functioning bike (not to a good one).
Of course there is a lot of C++, but it's the most important (as far as I understand) to collect it into one whole and to adapt it for trading purposes.
MQL5 C++ is a similar language, the developers did a great job to porting from C++ takes as little time as possible, there are a lot of implementations of neural networks in C++, so there are plenty of scooters.
It's the starship that needs to be planned. Otherwise what's the point of doing it all? (rhetorical question)
What is the point of the project?
There is an idea to develop a built-in neural network engine of several types, so that any trader could use it with minimal effort.
The code will be provided in source code of MQL5 and distributed as a part of the terminal.
However, how anyone can use something he knows next to nothing, and with minimal effort - I can't imagine. Yes, blondes (may blondes forgive me) drive a car, but they know some of its devices, they know the rules, and they drive it in the city, and they don't go out of town where there are no services. So "any trader" and even "with minimum effort" and with profit is not realistic imho, especially for a space plane.
What is the project for?
However, how anyone can use something he knows almost nothing about, and with minimal effort, I have no idea. Yes, blondes (may blondes forgive me) drive a car, but they know the rules and they drive it in the city and they don't go out of town where there are no services. So "any trader" and even "with minimum effort" and even "space plane" with profit is not realistic imho, especially for space plane.
The trader does not need to know how it works, he needs to know the minimum rules of use, our goal is to make these requirements as simple and intuitive as possible.
Man, of course the scooter is just the beginning. I mean, you have to start with a scooter. Eventually you'll get to the space plane faster by starting with a scooter now. You risk getting bogged down in the blueprints for a long time, if not forever.
And moving away from the scooter, part of the questions will be closed easily and part will fall away. And the audience will be able to go from the simple to the complex.
I will repeat my yesterday's post
Little imho while you have the lull. Ultimately, it is necessary to avoid the risk of creating a product that fully meets your needs in terms of functionality, but is completely unusable for the remaining 99% of potential users.
If we have to offer to the audience a new tool, it should ideally be suitable for everyone, well, for almost everyone, including those who have just opened the terminal, those who were using handwheel for years, and those who have two higher degrees and those who have textbooks.
If you were working with networks about 10 years ago, you should already refresh your knowledge in the relevant area before saying anything.
Have you invented anything fundamentally new during this time? And what success have you had in building a profitable NS for trading, since you are evaluating other people's knowledge? :)
No one has.
However you need to understand, for what they reduce the number of neurons in the layers and increase the number of examples in Sample (the essence is the same in both cases - reducing the degree of freedom of neurons) - of course to certain limits - until the network stops to learn.
Who needs this Sisyphean work to create a neural engine, if no one understands how to work with it in the simplest way? Looks like we'll have to write a manual for dummies on how to work effectively with the engine - like useful tips. Otherwise we will face a lot of accusations from ordinary users, traders: "I use neuro-engine, but my deposit is melting before my eyes - what's wrong with it? I'll complain!".
And you also need to understand the specifics of trading, that all inefficiencies are temporary and their properties change. That's why it makes no sense to be so bold to dispose of the number of examples in order to eliminate overtraining. Or do you naively hope to create an NS, which can be trained on any area or on any tool and it will be robust? :)
MQL5 C++ is a similar language, the developers did a great job to porting from C++ takes as little time as possible, there are a lot of implementations of neural networks in C++, so there are plenty of scooters.
It's the starship that needs to be planned. Otherwise what's the point of doing it all? (rhetorical question)
Man, of course the scooter is just the beginning. I mean, you have to start with a scooter. Eventually you'll get to the space plane faster by starting with a scooter now. You risk getting bogged down in the blueprints of a space plane for a long time, if not forever.
Has anything fundamentally new been invented during this time?