1 Attachment(s)
Category Theory in MQL5 (Part 11): Graphs
Quote:
In our previous article, we delved into monoid groups, by exploring concept of symmetry within typical monoids. In introducing an additional axiom that all members of a monoid group must possess an inverse and restricting binary operations between mirror elements to yield the identity element, we extended applicability of monoids at crucial trade decision points. Building upon this, we now continue our study of
category theory and its practical applications in trade system development by examining
graphs.
more...
Category Theory in MQL5 (Part 17): Functors and Monoids
Quote:
We continue our look at
category theory with one more take on
functors. So far, we have seen applications of category theory in implementing custom instances of the Expert trailing class, and the Expert Signal class so we will consider applications in using the Expert Money class for this article. All these classes come with the Meta Editor IDE and are used with the MQL5 wizard in assembling expert advisors with minimal coding.
In this article as we sum up our look at functors we’ll examine how when paired with
monoids and a pre-order of security prices, we can formulate a system to set position sizes when trading the a security, which will be BTCUSD (bitcoin).
more...
Wrapping ONNX models in classes
Quote:
In the previous
article, we used two ONNX models to arrange the voting classifier. The entire source text was organized as a single MQ5 file. The entire code was divided into functions. But what if we try to swap models? Or add another model? The original text will become even bigger. Let's try the object-oriented approach.
more...
Data label for time series mining(Part 1)
Quote:
When we design artificial intelligence models, we often need to prepare data first. Good data quality will allow us to get twice the result with half the effort in model training and validation. But our foreign exchange or stock data is special, which contains complex market information and time information, and data labeling is difficult, but we can easily analyze the trend in historical data on the chart.
This section introduces a method of making data sets with trend marks by EA operation charts, you can intuitively manipulate data according to your own ideas, of course you can also use the same method to expand and customize your own data sets!
more...
Neural networks made easy (Part 37): Sparse Attention
Quote:
In the previous article, we discussed relational models which use attention mechanisms in their architecture. We used this model to create an Expert Advisor, and the resulting EA showed good results. However, we noticed that the model's learning rate was lower compared to our earlier experiments. This is due to the fact that the transformer block used in the model is a rather complex architectural solution performing a large number of operations. The number of these operations grows in a quadratic progression as the size of the analyzed sequence increases, leading to an increase in memory consumption and model training time.
However, we recognize the limited resources available to improve the model. Therefore, there is a need to optimize the model with minimal loss of quality.
more...
Evaluating ONNX models using regression metrics
Quote:
Regression is a task of predicting a real value from an unlabeled example. A well-known example of regression is estimating the value of a diamond based on such characteristics as size, weight, color, clarity, etc.
The so-called
regression metrics are used to assess the accuracy of regression model predictions. Despite similar algorithms, regression metrics are semantically different from similar
loss functions.
more...
Neural networks made easy (Part 38): Self-Supervised Exploration via Disagreement
Quote:
This algorithm is based on a self-learning method, where the agent uses information obtained during interaction with the environment to generate "intrinsic" rewards and update its strategy. The algorithm is based on the use of several agent models that interact with the environment and generate various predictions. If the models disagree, it is considered an "interesting" event and the agent is incentivized to explore that space of the environment. In this way, the algorithm incentivizes the agent to explore new areas of the environment and allows it to make more accurate predictions about future rewards.
more...
Neural networks made easy (Part 39): Go-Explore, a different approach to exploration
Quote:
We continue the theme of environmental exploration in reinforcement learning. In previous articles within this series, we have already looked at algorithms for exploring the environment through curiosity and disagreement in an ensemble of models. Both approaches exploited intrinsic rewards to motivate the agent to perform different actions in similar situations while exploring new areas. But the problem is that the intrinsic reward decreases as the environment gets better explored. In complex cases of rare rewards, or when the agent may receive penalties on the way to the reward, this approach may not be very effective. In this article, I propose to get acquainted with a slightly different approach to studying the environment – the Go-Explore algorithm.
more...
Regression models of the Scikit-learn Library and their export to ONNX
Quote:
In this article, we will explore the application of regression models in the
Scikit-learn package, compute their parameters with double precision for the test dataset, attempt to convert them to the ONNX format for float and double precision, and use the obtained models in programs on MQL5. Additionally, we will compare the accuracy of the original models and their ONNX versions for float and double precision. Furthermore, we will examine the ONNX representation of regression models, which will provide a better understanding of their internal structure and operation.
more...
Data Science and Machine Learning (Part 18): The battle of Mastering Market Complexity, Truncated SVD Versus NMF
Quote:
According to Wikipedia, Dimensionality Reduction is the transformation of data from a high-dimensional space into a low dimensional space so that the low-dimensional representation retains some meaningful properties of the original data, ideally close to its intrinsic dimension.
more...
