Discussion of article "Third Generation Neural Networks: Deep Networks"

New comment
 

New article Third Generation Neural Networks: Deep Networks has been published:

This article is dedicated to a new and perspective direction in machine learning - deep learning or, to be precise, deep neural networks. This is a brief review of second generation neural networks, the architecture of their connections and main types, methods and rules of learning and their main disadvantages followed by the history of the third generation neural network development, their main types, peculiarities and training methods. Conducted are practical experiments on building and training a deep neural network initiated by the weights of a stacked autoencoder with real data. All the stages from selecting input data to metric derivation are discussed in detail. The last part of the article contains a software implementation of a deep neural network in an Expert Advisor with a built-in indicator based on MQL4/R.

This article is going to consider the main ideas of this subject such as Deep Learning and Deep Network without complex computations in layman’s terms.

Experiments with real data confirm (or don't) theoretical advantages of deep neural networks over shallow ones by metric definition and comparison (not sure about metric definition and comparison). The task in hand is classification. We shall create an indicator and an Expert Advisor based on a deep neural network model and working in conjunction according to the client/server scheme and then test them.

The reader is presumed to have a fair idea of the basic concepts used in neural networks.


4. The Implementation (Indicator and Expert Advisor)

Now we are going to write a program for the indicator and Expert Advisor using a deep network for receiving trading signals.

There are two ways of such an implementation:

  • The first one. Training of the neural network is performed in Rstudio manually. After obtaining acceptable results, save the network in the appropriate catalog. Then launch the EA and indicator on the chart. The EA will load the trained network. The indicator prepares a vector of new input data on each new bar and passes it to the EA. The EA presents network data, receives a signal and then acts on it. The EA is carrying on with its usual activities such as opening and closing orders, trailing etc The objective of the indicator is to prepare and pass on to the EA new input data on each new bar and, most importantly, present signals forecast by the network on a chart. Practice shows that visual control is the most efficient way of assessing a neural network.
  • Second way. Launch the EA and the indicator on the chart. At the first launch, the indicator passes on to the EA a prepared large set of input and output data. The EA launches training, testing and selecting the best neural network. After that work goes on like in the first way.

We are going to write the link indicator-EA following the first algorithm. EA with a minimum of bows and frills.

Why is it so difficult? This way of implementation allows to connect several indicators placed on different symbols/timeframes to one EA and work with them consequently. For that, the EA has to go through a little modernization. We are going to talk about it later.

Below is the structure of interaction between the indicator and the EA:

Fig. 31. Structure of interaction between the indicator and the EA

Fig. 31. Structure of interaction between the indicator and the EA

Author: Vladimir Perervenko

[Deleted]  

Thanks for the article. "It's a lot to take in all at once.

Question for the author. With regard to the construction of an Expert Advisor, is the number of coefficients to be adjusted with the logic of multiplying and adding up also off the scale here?

 
zaskok:

Thanks for the article. "It's a lot to take in all at once.

Question for the author. With regard to the construction of an Expert Advisor, is the number of coefficients to be adjusted with the logic of multiplying and adding up also off the scale here?

I don't understand the question. What are you talking about?
 
vlad1949:
I don't understand the question. What are you talking about?

CONGRATULATIONS!

Very informative and quality article!

 
faa1947:

CONGRATULATIONS!

Very informative and quality article!

Greetings.

We can use this example to understand clustering of input and matching clusters to the target cluster and other classification issues.

I will finish the calculation and post it

Good luck

[Deleted]  
vlad1949:
I don't understand the question. What are you talking about?
This.
 
vlad1949:

Greetings.

We can use this example to understand clustering of input and matching clusters to the target and other classification issues.

I will finish the calculation and post it

Good luck.

Very interesting. I would like to compare variants. Tried to understand clustering - it's just scary how many tools there are.
 

vlad1949:


...

  1. Indicator i_SAE.mq4, put it in the folder ~/MQL4/Indicators/
  2. Expert Advisor e_SAE.mq4, put it in the folder ~/MQL4/Experts/.
  3. Library mt4Rb7.dll, put it into the folder ~/MQL4/Libraries/.
  4. Header file mt4Rb7.mqh, put it into the folder ~/MQL4/Include/. The library and header file were developed and provided by a kind person Bernd Kreuss. In the name I added the index of the last change (b7). When there are many versions (like mine) with the same names, there are mishaps that take a lot of time to catch them.

...

I do not understand why to publish MQL4 developments in the category "Articles on programming in MQL5"?
 
Reshetov:
It is unclear why to publish MQL4 developments in the category "Articles on programming in MQL5"?

The question is not for me. Is that all you wanted to say about the article?

I am surprised.

Good luck

 
faa1947:
Very interesting. Would love to compare options. Tried to figure out the clustering - just a scary amount of tools.

That's true. But what is important here is not so much clustering itself as determining the optimal number of clusters into which we can (should) divide our set.

It's a lot of writing. Maybe I'll finish it tomorrow.

Good luck

[Deleted]  
zaskok:
About this.
I ask the author to make a great fit to the piece of history he has chosen and show the MQL-source (without DLL) of the EA. So that it would be possible to evaluate the essence of the EA, not just words.
1234567891011121314151617
New comment