mql5

In the previous articles (Part 1, Part 2, Part 3), we experimented with shapes and angles whose values were passed to the perceptron and the neural network built on the basis of the DeepNeuralNetwork.mqh library. We also conducted experiments on optimization methods in the strategy tester.
An important task in the current experiments was to track the influence of the amount of transmitted data and the depth of history we take this data from. In addition, we needed to reveal patterns, whether short or long templates are better, as well as whether we should use fewer or more parameters for passing.

more...
-------------------

• Experiments with neural networks (Part 1): Revisiting geometry
• Experiments with neural networks (Part 2): Smart neural network optimization
• Experiments with neural networks (Part 3): Practical application