Discussion of article "Neural networks made easy (Part 2): Network training and testing" - page 5

[Longsen Chen]

I have a simple question.

Why does these codes form a fractal?

if sell is true, candlestick (i+1) is a peak.

if buy is true, candlestick (i+1) is also a peak.

            bool sell=(High.GetData(i+2)<High.GetData(i+1) && High.GetData(i)<High.GetData(i+1));
            bool buy=(Low.GetData(i+2)<Low.GetData(i+1) && Low.GetData(i)<Low.GetData(i+1));
            TempData.Add(buy && !sell ? 1 : !buy && sell ? -1 : 0);

https://www.metatrader5.com/en/terminal/help/indicators/bw_indicators/fractals

According to the definition above, a fractal should have at least five successive bars

[rzicco]

MetaQuotes:

New article Neural networks made easy (Part 2): Network training and testing has been published:

Author: Dmitriy Gizlyk

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

[Dmitriy Gizlyk]

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.

[Chayakorn Rakwongthai]

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

[Too Chee Ng]

@ 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]

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.

[Too Chee Ng]

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.

[Retired57]

Hello everyone!

The series of articles is interesting and informative. read the theory and decided to move on to practice.

BUT!

my attempt to compile files from the 2nd part (Neural Networks - it's easy (Part 2): Network Training and Testing - MQL5 Articles ) was unsuccessful - 2 errors (see the trailer):

I would be grateful if you could tell me how to fix the error in the programme code or send correct files.

It's a shame. such a serious article and incorrect files.... (

[Gexon]

Retired57 #:

Hello, everyone!

The series of articles is interesting and informative. read the theory and decided to move on to practice.

BUT!

my attempt to compile files from Part 2 (Neural Networks - it's easy (Part 2): Network Training and Testing - MQL5 Articles ) was unsuccessful - 2 errors (see the trailer):

I would be grateful if you could tell me how to fix the error in the programme code or send correct files.

It's a shame. Such a serious article and incorrect files.... (

I removed the const keyword in the declarations of these methods and it compiled.

but I don't know how much it influenced the work of the programme)))))

[ZSH0811]

Shi Chao Ma #:
交易算法分三个等级，一级技术指标型（垃圾），二级大数据战略型（垃圾），三级逻辑必然型（无敌）。我的算法就是第三等级，安全性100%五个交易日加个零。

Shi Chao Ma #

:
Trading algorithms are divided into three levels, the first level of technical indicators (rubbish), the second level of big data strategy (rubbish), the third level of logical necessity (invincible). My algorithm is the third level, security 100% five trading days plus a zero.

You have the ability to write an article sun a code to see. Also five trading days plus a zero, TM Earth you the richest. Also logical inevitable, 100% security. You are the money plate, right?