Discussion of article "Neural networks made easy (Part 2): Network training and testing" - page 2

 
rzicco #:
I'm reading the neural net series of articles ... I can't find the links to the source files used in the articles, where can I find them? Thank you

At the bottom of article.

 

I receive 0.00 forecast using your AI i am not sure what am i missing? i try to learn how to code Machine learning base on your guidance

 

@ Dmitriy Gizlyk Very good training article.

I take that there would be a need to optimize the indicators' (RSI, MACD etc) parameters; may I know your advise on optimizing them please? Train/learn the NN first, then optimize the indicators' parameters? It takes a long time to train

/learn NN, how can we speed it up?

Many thanks for your time and advice.

Dmitriy Gizlyk
Dmitriy Gizlyk
  • 2023.06.07
  • www.mql5.com
Trader's profile
 
68360626 #:

@ Dmitriy Gizlyk Very good training article.

I take that there would be a need to optimize the indicators' (RSI, MACD etc) parameters; may I know your advise on optimizing them please? Train/learn the NN first, then optimize the indicators' parameters? It takes a long time to train

/learn NN, how can we speed it up?

Many thanks for your time and advice.

No. First you must optimize the parameters of the indicators or choose some other indicators. And then train NN on the new training data. You can use the correlation between indicator data and targets to select indicators and set them.

 
Dmitriy Gizlyk #:

No. First you must optimize the parameters of the indicators or choose some other indicators. And then train NN on the new training data. You can use the correlation between indicator data and targets to select indicators and set them.

Thanks Dmitriy Gizlyk for your reply.

I feel that using EA with indicators (RSI, MACD etc) to trade is not easy. It seems that it is even more complicated to use EA with indicators + NN. I.e. even harder to fine tune (indicators' parameter, plus NN's hyper-parameters etc.) the EA

What is your view on this please? How NN + indicators would help trading?

Hope you can give me some direction please.

Dmitriy Gizlyk
Dmitriy Gizlyk
  • 2023.06.07
  • www.mql5.com
Trader's profile
 

Thanks, Dmitriy.

What a fantastic article (and the preceding article)!  I was looking for something to get me started, some code that I can adapt, and this is perfect. I am new to MQL5, but I am already picking learning from reading the code. When compiling I had the same two errors as another poster, but thanks to Dmitriy's response I was able to edit NeuroNet.mqh and get a successful compilation.

Has anybody written the code to place orders? Care to share?

How could we also incorporate predicting which position open parameters would work best, such as volume, sl, and tp?

I love that there are only about 500 lines of code in both the example and the library. It's a manageable size for learning and adapting. 

Dmitriy Gizlyk
Dmitriy Gizlyk
  • 2024.04.19
  • www.mql5.com
Trader's profile
 
I am finding that Fractal_2 (classification) is displaying the highs and lows on the chart, but Fractal (regression) is not. Does anyone else have this issue?
 

I think I found the problem with the labels of the predicted fractals not being displayed for the regression neural network (Fractal).

The article says the following:

The variable i loops through the candles. This code is correct in the classification neural network (Fractal_2), although there the test is i<300.

However, in the regression neural network (Fractal), count is used as the test variable, and the test is ">".

Count seems to be the Era number. This would mean that labels would be placed on all relevant candles, not just those from the last 200, and only after 200 Eras. I assume this is an error.

Does this seem right?

A great learning experience.

 

Morning


Thank you so much for this article, however I ran into a compiler error compiling Fractal_2.mq5 and Fractal.mq5. The problem was "void  feedForward(const CArrayObj *&prevLayer);" and I changed it to "void feedForward(const CArrayObj *prevLayer);". Is this change correct

Regards

 
RenierVan #:

Morning


Thank you so much for this article, however I ran into a compiler error compiling Fractal_2.mq5 and Fractal.mq5. The problem was "void  feedForward(const CArrayObj *&prevLayer);" and I changed it to "void feedForward(const CArrayObj *prevLayer);". Is this change correct

Regards

Hi, yes, you can use it.