Neural networks, how to master them, where to start?

 
Hi all, I'm new to the forum. Ran through the forum a lot of useful stuff:). I wanted to ask the knowledgeable, I want to penetrate into the meaning of neural networks, but I do not know where to start while I have a general idea read an article by Reshetov, now I want to develop in this direction. Popeopeye useful literature on this subject, maybe somewhere on a forum is, but I have not looked up? Thanks in advance:)
 
In the top right-hand corner there's a good service called 'Search'. Carefully type in your favourite word and you'll discover much more......))))
 
The same would apply to Yandex. Jokes are jokes, but the topic has been brought up more than once.
 
I'm sorry, I just need a book or other information where everything is in a nutshell and no water, you've been studying and you should know better what is written to understand and what is not worth reading so as not to mess with your head...
 
LeoV >> :
There is a nice service called "Search" in the top right corner. Carefully type in your favourite word and you'll discover a lot of new things......))))

I understand about search... I'm currently reading a book about neural networks, but I still do not understand how to implement it in mql4.

Let us take a simple algorithm that gives entry points for Stop Loss and Take Profit based on the last fractal:

If we have a fractal upwards, we put a Buy Stop order for a fractal breakout, with a stop loss below the minimum price among the bars from zero to the bar at which the fractal was formed. Take profit is equal to the stop loss.

This algorithm can identify several reference points, based on which the fractal model will be measured:


Parameters that can be used as weights:
To buy:
iUpFr
iUpFr-iSellSl
UpFr-SellSl
(UpFr-SellSl)/(iUpFr-iSellSl)
(UpFr-SellSl)/(iUpFr)

For Sell:
iDnFr
iDnFr-iBuySl
BuySl-DnFr
(BuySl-DnFr)/(iDnFr-iBuySl)
(BuySl-DnFr)/(iDnFr)

Do I understand correctly that the next step in creating the neural network is to introduce variables to be compared against these properties?

Will the comparison take place during the optimisation process?

 
danja >> :
Hi all, I'm new to the forum here. Ran through the forum a lot of useful stuff:). I wanted to ask the knowledgeable, I want to penetrate into the meaning of neural networks, but do not know where to start while I have a general idea read an article by Reshetov, now there is a desire to develop in this direction. Possible useful literature on this topic, maybe somewhere on the forum is, but I have not looked up? Thanks in advance:)

I decided for myself that the study of neural networks should begin with their writing. I now sculpt a multilayer pseptron (I hope I got it right :)). And I advise you to do the same.

 
arnautov >> :

I've decided for myself that studying neural networks should start with writing them. I'm making a multilayer Perspectron (I hope I got it right :)). I advise you to do the same.

Let's try to write a simple neural network together, lay it all out... and experienced pragmists can give us some tips...

 
danja писал(а) >>
I apologize of course, I just need a book or other information where everything is in clear lines and no water... You're the one who studied and you should know better what is written for understanding and what shouldn't be read so as not to mess up your head.

Neural networks are such a thing, there's nothing without water) And there's nothing in the detail. Besides water, there is severe mathematics, which is not easy to understand, and maybe not everyone can... And there cannot be a beaten path here, only directions.

https://ru.wikipedia.org/wiki/Категория:Нейросети

http://www.neuroproject.ru/

http://iit.ntu-kpi.kiev.ua/Neuro/ru/lib_ru.htm

And it's up to the curve of your inquisitiveness...

Andrey4-min wrote >>

So let's try to write a simple neural network together, lay it all out... and experienced pragrammers will give us some tips...

Everything has been "stolen" before us... Have a look.

http://www.fxreal.ru/forums/forums.php?forum=2

 

What's there to think about - you have to shake it,

-Download NeuroShell 2 with the "wrong LeoV" avatar and go!!!

 
I'm also interested in neural networks, I've read and understood them... I tried to use a probability network in codebase libraries, but nothing came out... you have to start from the simplest one, it's complicated.... You can't say for sure if the price will go up or down? .... Yes, you should know how to use them
Reason: