![Neural networks made easy (Part 23): Building a tool for Transfer Learning](https://c.mql5.com/2/49/Neural_Networks_Easy_015_600x314.jpg)
Neural networks made easy (Part 23): Building a tool for Transfer Learning
In this series of articles, we have already mentioned Transfer Learning more than once. However, this was only mentioning. in this article, I suggest filling this gap and taking a closer look at Transfer Learning.
![DoEasy. Controls (Part 30): Animating the ScrollBar control](https://c.mql5.com/2/51/doeasy_030_600x314.jpg)
DoEasy. Controls (Part 30): Animating the ScrollBar control
In this article, I will continue the development of the ScrollBar control and start implementing the mouse interaction functionality. In addition, I will expand the lists of mouse state flags and events.
![Data Science and Machine Learning (Part 22): Leveraging Autoencoders Neural Networks for Smarter Trades by Moving from Noise to Signal](https://c.mql5.com/2/77/Data_Science_and_ML_9Part_22t_600x314.jpg)
Data Science and Machine Learning (Part 22): Leveraging Autoencoders Neural Networks for Smarter Trades by Moving from Noise to Signal
In the fast-paced world of financial markets, separating meaningful signals from the noise is crucial for successful trading. By employing sophisticated neural network architectures, autoencoders excel at uncovering hidden patterns within market data, transforming noisy input into actionable insights. In this article, we explore how autoencoders are revolutionizing trading practices, offering traders a powerful tool to enhance decision-making and gain a competitive edge in today's dynamic markets.
![Neural networks made easy (Part 20): Autoencoders](https://c.mql5.com/2/49/Neural_Networks_Easy_012_600x314.jpg)
Neural networks made easy (Part 20): Autoencoders
We continue to study unsupervised learning algorithms. Some readers might have questions regarding the relevance of recent publications to the topic of neural networks. In this new article, we get back to studying neural networks.
![Timeseries in DoEasy library (part 57): Indicator buffer data object](https://c.mql5.com/2/49/doeasy_057_600x314.jpg)
Timeseries in DoEasy library (part 57): Indicator buffer data object
In the article, develop an object which will contain all data of one buffer for one indicator. Such objects will be necessary for storing serial data of indicator buffers. With their help, it will be possible to sort and compare buffer data of any indicators, as well as other similar data with each other.
![Developing a trading Expert Advisor from scratch (Part 23): New order system (VI)](https://c.mql5.com/2/49/Developing_a_trading_Expert_Advisor_002_600x314.jpg)
Developing a trading Expert Advisor from scratch (Part 23): New order system (VI)
We will make the order system more flexible. Here we will consider changes to the code that will make it more flexible, which will allow us to change position stop levels much faster.
![Neural networks made easy (Part 50): Soft Actor-Critic (model optimization)](https://c.mql5.com/2/57/NN_50_Soft_Actor-Critic_600x314.jpg)
Neural networks made easy (Part 50): Soft Actor-Critic (model optimization)
In the previous article, we implemented the Soft Actor-Critic algorithm, but were unable to train a profitable model. Here we will optimize the previously created model to obtain the desired results.
![Neural networks made easy (Part 38): Self-Supervised Exploration via Disagreement](https://c.mql5.com/2/54/self_supervised_exploration_via_disagreement_038_600x314.jpg)
Neural networks made easy (Part 38): Self-Supervised Exploration via Disagreement
One of the key problems within reinforcement learning is environmental exploration. Previously, we have already seen the research method based on Intrinsic Curiosity. Today I propose to look at another algorithm: Exploration via Disagreement.
![Design Patterns in software development and MQL5 (Part I): Creational Patterns](https://c.mql5.com/2/60/Creational_Patterns__2_600x314.jpg)
Design Patterns in software development and MQL5 (Part I): Creational Patterns
There are methods that can be used to solve many problems that can be repeated. Once understand how to use these methods it can be very helpful to create your software effectively and apply the concept of DRY ((Do not Repeat Yourself). In this context, the topic of Design Patterns will serve very well because they are patterns that provide solutions to well-described and repeated problems.
![How to build and optimize a volatility-based trading system (Chaikin Volatility - CHV)](https://c.mql5.com/2/76/How_to_build_and_optimize_a_volatility-based_trading_system_cChaikin_Volatility_-_CHVq_600x314.jpg)
How to build and optimize a volatility-based trading system (Chaikin Volatility - CHV)
In this article, we will provide another volatility-based indicator named Chaikin Volatility. We will understand how to build a custom indicator after identifying how it can be used and constructed. We will share some simple strategies that can be used and then test them to understand which one can be better.
![Developing a trading Expert Advisor from scratch (Part 27): Towards the future (II)](https://c.mql5.com/2/49/Developing_a_trading_Expert_Advisor_006_600x314.jpg)
Developing a trading Expert Advisor from scratch (Part 27): Towards the future (II)
Let's move on to a more complete order system directly on the chart. In this article, I will show a way to fix the order system, or rather, to make it more intuitive.
![Neural networks made easy (Part 43): Mastering skills without the reward function](https://c.mql5.com/2/54/NN_Simple_Part_43_600x314.jpg)
Neural networks made easy (Part 43): Mastering skills without the reward function
The problem of reinforcement learning lies in the need to define a reward function. It can be complex or difficult to formalize. To address this problem, activity-based and environment-based approaches are being explored to learn skills without an explicit reward function.
![How to Integrate Smart Money Concepts (BOS) Coupled with the RSI Indicator into an EA](https://c.mql5.com/2/83/Integrate_Smart_Money_Concepts_coupled_with_the_RSI_Indicator_into_an_EA_600x314.jpg)
How to Integrate Smart Money Concepts (BOS) Coupled with the RSI Indicator into an EA
Smart Money Concept (Break Of Structure) coupled with the RSI Indicator to make in informed automated trading decisions based on the market structure.
![Vladimir Tsyrulnik: The Essense of my program is improvisation! (ATC 2010)](https://c.mql5.com/2/0/ustas_ava.png)
![Vladimir Tsyrulnik: The Essense of my program is improvisation! (ATC 2010)](https://c.mql5.com/i/articles/overlay.png)
Vladimir Tsyrulnik: The Essense of my program is improvisation! (ATC 2010)
Vladimir Tsyrulnik is the holder of one of the brightest highs of the current Championship. By the end of the third trading week Vladimir's Expert Advisor was on the sixth position. The IMEX algorithm the Expert Advisor is based on was developed by Vladimir. To learn more about this algorithm, we had an interview with Vladimir.
![Population optimization algorithms: Firefly Algorithm (FA)](https://c.mql5.com/2/51/firefly_algorithm_600x314.jpg)
Population optimization algorithms: Firefly Algorithm (FA)
In this article, I will consider the Firefly Algorithm (FA) optimization method. Thanks to the modification, the algorithm has turned from an outsider into a real rating table leader.
![Interview with Alexander Topchylo (ATC 2010)](https://c.mql5.com/2/0/35.png)
![Interview with Alexander Topchylo (ATC 2010)](https://c.mql5.com/i/articles/overlay.png)
Interview with Alexander Topchylo (ATC 2010)
Alexander Topchylo (Better) is the winner of the Automated Trading Championship 2007. Alexander is an expert in neural networks - his Expert Advisor based on a neural network was on top of best EAs of year 2007. In this interview Alexander tells us about his life after the Championships, his own business and new algorithms for trading systems.
![Interview with Tim Fass (ATC 2011)](https://c.mql5.com/2/0/avatar_Tim.png)
![Interview with Tim Fass (ATC 2011)](https://c.mql5.com/i/articles/overlay.png)
Interview with Tim Fass (ATC 2011)
A student from Germany Tim Fass (Tim) is participating in the Automated Trading Championship for the first time. Nevertheless, his Expert Advisor The_Wild_13 already got featured at the very top of the Championship rating and seems to be holding his position in the top ten. Tim told us about his Expert Advisor, his faith in the success of simple strategies and his wildest dreams.
![Statistical Arbitrage with predictions](https://c.mql5.com/2/77/Statistical_Arbitrage_with_predictions_600x314.jpg)
Statistical Arbitrage with predictions
We will walk around statistical arbitrage, we will search with python for correlation and cointegration symbols, we will make an indicator for Pearson's coefficient and we will make an EA for trading statistical arbitrage with predictions done with python and ONNX models.
![Custom Indicators (Part 1): A Step-by-Step Introductory Guide to Developing Simple Custom Indicators in MQL5](https://c.mql5.com/2/76/Custom_Indicators_hPart_1q_600x314.jpg)
Custom Indicators (Part 1): A Step-by-Step Introductory Guide to Developing Simple Custom Indicators in MQL5
Learn how to create custom indicators using MQL5. This introductory article will guide you through the fundamentals of building simple custom indicators and demonstrate a hands-on approach to coding different custom indicators for any MQL5 programmer new to this interesting topic.
![Do Traders Need Services From Developers?](https://c.mql5.com/2/10/MQL5_freelance_avatar.png)
![Do Traders Need Services From Developers?](https://c.mql5.com/i/articles/overlay.png)
Do Traders Need Services From Developers?
Algorithmic trading becomes more popular and needed, which naturally led to a demand for exotic algorithms and unusual tasks. To some extent, such complex applications are available in the Code Base or in the Market. Although traders have simple access to those apps in a couple of clicks, these apps may not satisfy all needs in full. In this case, traders look for developers who can write a desired application in the MQL5 Freelance section and assign an order.
![Python, ONNX and MetaTrader 5: Creating a RandomForest model with RobustScaler and PolynomialFeatures data preprocessing](https://c.mql5.com/2/61/Python_ONNX__MetaTrader_5____RandomForest__600x314.jpg)
Python, ONNX and MetaTrader 5: Creating a RandomForest model with RobustScaler and PolynomialFeatures data preprocessing
In this article, we will create a random forest model in Python, train the model, and save it as an ONNX pipeline with data preprocessing. After that we will use the model in the MetaTrader 5 terminal.
![Automated Parameter Optimization for Trading Strategies Using Python and MQL5](https://c.mql5.com/2/82/Automated_Parameter_Optimization_for_Trading_Strategies_Using_Python_and_MQL5___2_600x314.jpg)
Automated Parameter Optimization for Trading Strategies Using Python and MQL5
There are several types of algorithms for self-optimization of trading strategies and parameters. These algorithms are used to automatically improve trading strategies based on historical and current market data. In this article we will look at one of them with python and MQL5 examples.
![How to create a simple Multi-Currency Expert Advisor using MQL5 (Part 7): ZigZag with Awesome Oscillator Indicators Signal](https://c.mql5.com/2/73/How_to_create_a_simple_Multi-Currency_Expert_Advisor_using_MQL5__Part_7_600x314.jpg)
How to create a simple Multi-Currency Expert Advisor using MQL5 (Part 7): ZigZag with Awesome Oscillator Indicators Signal
The multi-currency expert advisor in this article is an expert advisor or automated trading that uses ZigZag indicator which are filtered with the Awesome Oscillator or filter each other's signals.
![DoEasy. Controls (Part 5): Base WinForms object, Panel control, AutoSize parameter](https://c.mql5.com/2/49/doeasy_005_600x314.jpg)
DoEasy. Controls (Part 5): Base WinForms object, Panel control, AutoSize parameter
In the article, I will create the base object of all library WinForms objects and start implementing the AutoSize property of the Panel WinForms object — auto sizing for fitting the object internal content.
![Alexander Anufrenko: "A danger foreseen is half avoided" (ATC 2010)](https://c.mql5.com/2/0/anufrenko_ava.png)
![Alexander Anufrenko: "A danger foreseen is half avoided" (ATC 2010)](https://c.mql5.com/i/articles/overlay.png)
Alexander Anufrenko: "A danger foreseen is half avoided" (ATC 2010)
The risky development of Alexander Anufrenko (Anufrenko321) had been featured among the top three of the Championship for three weeks. Having suffered a catastrophic Stop Loss last week, his Expert Advisor lost about $60,000, but now once again he is approaching the leaders. In this interview the author of this interesting EA is describing the operating principles and characteristics of his application.
![Interview with Andrea Zani (ATC 2011)](https://c.mql5.com/2/0/ava__2.png)
![Interview with Andrea Zani (ATC 2011)](https://c.mql5.com/i/articles/overlay.png)
Interview with Andrea Zani (ATC 2011)
On the eleventh week of the Automated Trading Championship, Andrea Zani (sbraer) got featured very close to the top five of the competition. It is on the sixth place with about 47,000 USD now. Andrea's Expert Advisor AZXY has made only one losing deal, which was at the very beginning of the Championship. Since then, its equity curve has been steadily growing.
![Integrate Your Own LLM into EA (Part 2): Example of Environment Deployment](https://c.mql5.com/2/59/Example_of_Environment_Deployment_600x314.jpg)
Integrate Your Own LLM into EA (Part 2): Example of Environment Deployment
With the rapid development of artificial intelligence today, language models (LLMs) are an important part of artificial intelligence, so we should think about how to integrate powerful LLMs into our algorithmic trading. For most people, it is difficult to fine-tune these powerful models according to their needs, deploy them locally, and then apply them to algorithmic trading. This series of articles will take a step-by-step approach to achieve this goal.
![Andrey Bolkonsky (abolk): "Any programmer knows that there is no software without bugs"](https://c.mql5.com/2/0/Interview_Andrey_Bolkonsky.png)
![Andrey Bolkonsky (abolk): "Any programmer knows that there is no software without bugs"](https://c.mql5.com/i/articles/overlay.png)
Andrey Bolkonsky (abolk): "Any programmer knows that there is no software without bugs"
Andrey Bolkonsky (abolk) has been participating in the Jobs service since its opening. He has developed dozens of indicators and Expert Advisors for the MetaTrader 4 and MetaTrader 5 platforms. We will talk with Andrey about what a server is from the perspective of a programmer.
![Population optimization algorithms: Cuckoo Optimization Algorithm (COA)](https://c.mql5.com/2/50/Cuckoo-Optimization-Algorithm-cover_600x314.jpg)
Population optimization algorithms: Cuckoo Optimization Algorithm (COA)
The next algorithm I will consider is cuckoo search optimization using Levy flights. This is one of the latest optimization algorithms and a new leader in the leaderboard.
![Developing an MQTT client for MetaTrader 5: a TDD approach — Part 3](https://c.mql5.com/2/58/mqtt_p3_600x314.jpg)
Developing an MQTT client for MetaTrader 5: a TDD approach — Part 3
This article is the third part of a series describing our development steps of a native MQL5 client for the MQTT protocol. In this part, we describe in detail how we are using Test-Driven Development to implement the Operational Behavior part of the CONNECT/CONNACK packet exchange. At the end of this step, our client MUST be able to behave appropriately when dealing with any of the possible server outcomes from a connection attempt.
![Neural networks made easy (Part 35): Intrinsic Curiosity Module](https://c.mql5.com/2/50/Neural_Networks_Made_035_600x314.jpg)
Neural networks made easy (Part 35): Intrinsic Curiosity Module
We continue to study reinforcement learning algorithms. All the algorithms we have considered so far required the creation of a reward policy to enable the agent to evaluate each of its actions at each transition from one system state to another. However, this approach is rather artificial. In practice, there is some time lag between an action and a reward. In this article, we will get acquainted with a model training algorithm which can work with various time delays from the action to the reward.
![Experiments with neural networks (Part 4): Templates](https://c.mql5.com/2/52/neural_network_experiments-004_600x314.jpg)
Experiments with neural networks (Part 4): Templates
In this article, I will use experimentation and non-standard approaches to develop a profitable trading system and check whether neural networks can be of any help for traders. MetaTrader 5 as a self-sufficient tool for using neural networks in trading. Simple explanation.
![Neural networks made easy (Part 75): Improving the performance of trajectory prediction models](https://c.mql5.com/2/68/Neural_Networks_Made_Easy_5Part_75d_Improving_the_Performance_of_Trajectory_Prediction_Models_600x31.jpg)
Neural networks made easy (Part 75): Improving the performance of trajectory prediction models
The models we create are becoming larger and more complex. This increases the costs of not only their training as well as operation. However, the time required to make a decision is often critical. In this regard, let us consider methods for optimizing model performance without loss of quality.
![Multilayer perceptron and backpropagation algorithm (Part 3): Integration with the Strategy Tester - Overview (I).](https://c.mql5.com/2/51/Perceptron_Multicamadas_e_o_Algoritmo_Backpropagation_600x314.jpg)
Multilayer perceptron and backpropagation algorithm (Part 3): Integration with the Strategy Tester - Overview (I).
The multilayer perceptron is an evolution of the simple perceptron which can solve non-linear separable problems. Together with the backpropagation algorithm, this neural network can be effectively trained. In Part 3 of the Multilayer Perceptron and Backpropagation series, we'll see how to integrate this technique into the Strategy Tester. This integration will allow the use of complex data analysis aimed at making better decisions to optimize your trading strategies. In this article, we will discuss the advantages and problems of this technique.
![Understand and Efficiently use OpenCL API by Recreating built-in support as DLL on Linux (Part 2): OpenCL Simple DLL implementation](https://c.mql5.com/2/53/Recreating-built-in-OpenCL-p3_600x314.jpg)
Understand and Efficiently use OpenCL API by Recreating built-in support as DLL on Linux (Part 2): OpenCL Simple DLL implementation
Continued from the part 1 in the series, now we proceed to implement as a simple DLL then test with MetaTrader 5. This will prepare us well before developing a full-fledge OpenCL as DLL support in the following part to come.
![Category Theory in MQL5 (Part 20): A detour to Self-Attention and the Transformer](https://c.mql5.com/2/58/Category-Theory-p20_600x314.jpg)
Category Theory in MQL5 (Part 20): A detour to Self-Attention and the Transformer
We digress in our series by pondering at part of the algorithm to chatGPT. Are there any similarities or concepts borrowed from natural transformations? We attempt to answer these and other questions in a fun piece, with our code in a signal class format.
![Dimitar Manov: "I fear only extraordinary situations in the Championship" (ATC 2010)](https://c.mql5.com/2/0/manov_avatar.png)
![Dimitar Manov: "I fear only extraordinary situations in the Championship" (ATC 2010)](https://c.mql5.com/i/articles/overlay.png)
Dimitar Manov: "I fear only extraordinary situations in the Championship" (ATC 2010)
In the recent review by Boris Odintsov the Expert Advisor of the Bulgarian Participant Dimitar Manov appeared among the most stable and reliable EAs. We decided to interview this developer and try to find the secret of his success. In this interview Dimitar has told us what situation would be unfavorable for his robot, why he's not using indicators and whether he is expecting to win the competition.
![Developing a Replay System (Part 27): Expert Advisor project — C_Mouse class (I)](https://c.mql5.com/2/58/Projeto_Expert_AdvisorcClasse_C_Mous_600x314.jpg)
Developing a Replay System (Part 27): Expert Advisor project — C_Mouse class (I)
In this article we will implement the C_Mouse class. It provides the ability to program at the highest level. However, talking about high-level or low-level programming languages is not about including obscene words or jargon in the code. It's the other way around. When we talk about high-level or low-level programming, we mean how easy or difficult the code is for other programmers to understand.
![Brute force approach to patterns search (Part V): Fresh angle](https://c.mql5.com/2/57/The_Bruteforce_Approach_Part_5_600x314.jpg)
Brute force approach to patterns search (Part V): Fresh angle
In this article, I will show a completely different approach to algorithmic trading I ended up with after quite a long time. Of course, all this has to do with my brute force program, which has undergone a number of changes that allow it to solve several problems simultaneously. Nevertheless, the article has turned out to be more general and as simple as possible, which is why it is also suitable for those who know nothing about brute force.
![Introduction to MQL5 (Part 4): Mastering Structures, Classes, and Time Functions](https://c.mql5.com/2/70/Introduction_to_MQL5_pPart_4c_Mastering_Structuresq_Classesf_and_Time_Functions_600x314.jpg)
Introduction to MQL5 (Part 4): Mastering Structures, Classes, and Time Functions
Unlock the secrets of MQL5 programming in our latest article! Delve into the essentials of structures, classes, and time functions, empowering your coding journey. Whether you're a beginner or an experienced developer, our guide simplifies complex concepts, providing valuable insights for mastering MQL5. Elevate your programming skills and stay ahead in the world of algorithmic trading!