Neural Networks - page 27

[Sergey Golubev]

1. Neural networks made easy - MT5
2. Neural networks made easy (Part 2): Network training and testing - MT5
3. Neural networks made easy (Part 3): Convolutional networks - MT5
4. Neural networks made easy (Part 4): Recurrent networks - MT5
5. Neural networks made easy (Part 5): Multithreaded calculations in OpenCL - MT5 
6. Neural networks made easy (Part 6): Experimenting with the neural network learning rate - MT5
7. Neural networks made easy (Part 7): Adaptive optimization methods - MT5
   
8. Neural networks made easy (Part 8): Attention mechanisms - MT5
9. Neural networks made easy (Part 9): Documenting the work - MT5 
10. Neural networks made easy (Part 10): Multi-Head Attention - MT5
    
11. Neural networks made easy (Part 11): A take on GPT - MT5
    
12. Neural networks made easy (Part 12): Dropout - MT5
    
13. Neural networks made easy (Part 13): Batch Normalization - MT5
    

[Sergey Golubev]

Forum on trading, automated trading systems and testing trading strategies

Taking Neural Networks to the next level

Sergey Golubev, 2021.04.13 10:14

Machine learning in Grid and Martingale trading systems. Would you bet on it? - MT5

We have been working hard studying various approaches to using machine learning aimed at finding patterns in the forex market. You already know how to train models and implement them. But there are a large number of approaches to trading, almost every one of which can be improved by applying modern machine learning algorithms. One of the most popular algorithms is the grid and/or martingale. Before writing this article, I did a little exploratory analysis, searching for the relevant information on the Internet. Surprisingly, this approach has little to no coverage in the global network. I had a little survey among the community members regarding the prospects of such a solution, and the majority answered that they did not even know how to approach this topic, but the idea itself sounded interesting. Although, the idea itself seems quite simple.

Let us conduct a series of experiments with two purposes. First, we will try to prove that this is not as difficult as it might seem at first glance. Second, we will try to find out if this approach is applicable and effective. 

[Sergey Golubev]

Neural networks made easy (Part 12): Dropout

Since the beginning of this series of articles, we have already made a big progress in studying various neural network models. But the learning process was always performed without our participation. At the same time, there is always a desire to somehow help the neural network to improve training results, which can also be referred to as the convergence of the neural network. In this article we will consider one of such methods entitled Dropout.

Contents

• Introduction
• 1. Dropout: A Method for Increasing Neural Network Convergence
• 2. Implementation
• 2.1. Creating a New Class for Our Model
• 2.2. Feed-Forward
• 2.3. Feed-Backward
• 2.4. Class Saving and Loading Methods
• 2.5. Changes in the Neural Network Base Classes
• 3. Test
• Conclusion
• References
• Programs Used in the Article

[Sergey Golubev]

Neural networks made easy (Part 13): Batch Normalization

In the previous article, we started considering methods aimed at increasing the convergence of neural networks and got acquainted with the Dropout method, which is used to reduce the co-adaptation of features. Let us continue this topic and get acquainted with the methods of normalization.

Contents

• Introduction
• 1. Theoretical Prerequisites for Normalization
• 2. Implementation
• 2.1. Creating a New Class for Our Model
• 2.2. Feed-Forward
• 2.3. Feed-Backward
• 2.4. Changes in the Neural Network Base Classes
• 3. Testing
• Conclusion
• References
• Programs Used in the Article

[Sergey Golubev]

Forum on trading, automated trading systems and testing trading strategies

Taking Neural Networks to the next level

Sergey Golubev, 2021.10.20 11:21

Programming a Deep Neural Network from Scratch using MQL Language 

Since machine learning has recently gained popularity, many have heard about Deep Learning and desire to know how to apply it in the MQL language. I have seen simple implementations of artificial neurons with activation functions, but nothing that implements a real Deep Neural Network. In this article, I will introduce to you a Deep Neural Network implemented in the MQL language with its different activation functions, such as the hyperbolic tangent function for the hidden layers and the Softmax function for the output layer. We will move from the first step through the end to completely form the Deep Neural Network.

[votija.63]

Hello Sergey Golubev: I would like to wish you happy holidays, I read your articles and references a lot, do you know any programmer who has the experience of doing work with neurals? I use 3 indicators, which when aligned, is very profitable !!, Thank you very much for any information, a hug!

[Sergey Golubev]

How to master Machine Learning

All beginning traders start their learning journey with the technical analysis basics, and many of them read the same books on stock exchange trading. The basics are normally easy to understand. However, the initial manual trading phase passes fairly quickly. The next step is to achieve greater stability of trading results and to increase trading volumes, while covering a variety of financial instruments and maintaining low risk. This is where algorithmic trading via trading robots comes in handy, which is however a totally new area of study. In addition to financial market knowledge, it requires programming and technical analysis skills.

----------------

This is the key and summary article about Machine Learning with the books, online courses and specializations, youTube videos, blogs and relevant websites, interviews, scientific papers, and more.

[Sergey Golubev]

Data Science and Machine Learning — Neural Network (Part 01): Feed Forward Neural Network demystified

Neural networks sound like this fancy new thing that seems as a way forward to build holy grails trading systems, many traders are stunned by the programs made of neural networks, as they seem to be good at predicting market movements basically, they are good at any task at hand.

In this article, we are going to see the basics of a neural network and answer some of the basic questions that I think are important for an ML enthusiast to understand for them to master this subject.

[Sergey Golubev]

Data Science and Machine Learning — Neural Network (Part 02): Feed forward NN Architectures Design 

In the prior article, we discussed the basics of a neural network and build a very basic and static MLP, but we know in real-life applications we are not going to need a simple 2 inputs and 2 hidden layers nodes in the network to the output, something we built last time.
My point is that we need something dynamic. A dynamic code that we can change the parameters and optimize without breaking the program. If you use python-keras library to build a neural network you will have to do less work of configuring and compiling even complex architectures, that is something that I want us to be able to achieve in MQL5.

Just like I did on the Linear regression part 3 which is one among the must-read in this article series, I introduced the matrix/vector form of models to be able to have flexible models with an unlimited number of inputs.

-------------------

• Data Science and Machine Learning — Neural Network (Part 01): Feed Forward Neural Network demystified
• Data Science and Machine Learning — Neural Network (Part 02): Feed forward NN Architectures Design

[Sergey Golubev]

Measuring Indicator Information

Machine learning relies on training data to learn the general behaviour of the market to ultimately make fairly accurate predictions. The chosen learning algorithm has to wade through a carefully selected sample to extract meaningful information. Indicators can be thought of as purveyors of information about the underlying price series they are applied to. Using this premise, entropy can be used to measure how much information is communicated by an indicator. Using steps and tools documented in the book, Testing and Tuning Market Trading Systems (TTMTS) written by Timothy Masters, we will demonstrate how these can be used to evaluate the structure of indicator data.