All about MQL5 Wizard : create robots without programming. - page 5

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 23): CNNs

CNNs are typically complex neural networks whose main applications are in video and image processing, like we saw with GANs in the previous article. However, unlike GANs that are trained in identifying real images and or subjects in the images from fakes, CNNs tend to work more like a classifier in that they split the input data (which is often image pixels) into various subgroups of data whereby each subgroup is meant to capture a key or very important property of the input data. These produced subgroups are often referred to as feature maps.

[Marvin79]

I also found this!

<...>

[Sergey Golubev]

Marvin79 #:

I got one too!

<...>

This is from CodeBase:

MQL5 Wizard MA RSI - Expert Advisor for MetaTrader 5

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 24): Moving Averages

We continue this series on MQL5 Wizards by looking at the moving average indicator and how it could be added to the library of tools already available in ways that could be novel to some traders. The Moving Average has very many variants as a single time series attachable to a chart, but also other variants as an oscillator and even others an envelopes' indicator.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 25): Multi-Timeframe Testing and Trading

In our last article we looked at Pythagorean Means which are a group of moving averages of which some are quite novel and not common enough despite their potential in benefiting some traders as we hinted in the test reports. These Pythagorean Means were represented in a semicircle diagram that summarized what each mean value was when presented with two unequal values that added up to the diameter of the semicircle. Among the chord values in the semicircle that was not touched on in the article was the value indicated as Q that represented the quadratic mean of the two values a and b.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 26): Moving Averages and the Hurst Exponent

We continue this series on techniques with the MQL5 wizard that focus on alternative methods in Financial time series analysis for the benefit of traders. For this article, we consider the Hurst Exponent. This is a metric which tells us whether a time series has a high positive autocorrelation or a negative autocorrelation over the long term. The applications of this measurement can be very extensive. How would we use it? Well, firstly, we’d calculate the Hurst exponent to determine if the market is trending (which would typically give us a value greater than 0.5) or if the market is mean-reverting/ whipsawed (that would give us a value less than 0.5). For this article, since we are in a ‘season of looking at moving averages’ given the last pair of articles, we will marry the Hurst Exponent information with the relative position of the current price to a moving average. The relative position of price to a moving average can be indicative of price’s next direction, with one major caveat.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 27): Moving Averages and the Angle of Attack 

We continue the series on trade setups and ideas that can be quickly tested and fool-proofed thanks to the MQL5 wizard by considering the angle of attack. Broadly, the phrase ‘angle of attack’ is associated with the ideal angle at which a fighter jet ought to take off, when optimizing for maximum air lift and minimum fuel consumption.

We as always use an instance of a custom signal class to test our hypotheses on how to measure the attack angle, and we measure this angle not off of raw price but a moving average. We use the decaying moving average as our indicator for measuring and tracking the significance of the attack angle. Raw prices can also be used to monitor attack angles, however since they are bound to have more volatile values than an indicator buffer, we adopt the former. Any moving average could have been used as well, but we adopted the decaying moving average because it is a bit novel and may not be familiar to most traders.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 28): GANs Revisited with a Primer on Learning Rates

We revisit a form of neural network we had considered in an earlier article by dwelling on one specific hyperparameter. The learning-rate. The Generative Adversarial Network is a neural network that operates in pairs, where one network is trained traditionally to discern the truth, while another is trained to discern the former’s projections from real occurrences. This duality does imply that the traditionally trained network (the former) is trying to fool the latter and this is true, however the two networks are on the ‘same team’ and the simultaneous training of both ultimately makes the generator network more useful to the trader. For this article, we dwell on the training process by focusing on the learning rate.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 29): Continuation on Learning Rates with MLPs

We revisit and conclude our look at the role different formats of learning rates have on Expert Advisor performance by examining the adaptive learning rates and the one cycle learning rate. The format for this article will follow the approach we had in the last article by having test reports at each learning rate format section rather than at the end of the article.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 30): Spotlight on Batch-Normalization in Machine Learning

This article, like all in this series, highlights the use of wizard assembled Expert Advisors in testing out new ideas. Introductions on how this is done can be got from here and here for new readers, with those 2 articles providing some guidance on how to use the code attached at the end of this article. For this piece, we are using quite a few custom enumerations of data as optimizable inputs. The MQL5 inbuilt enumerations can be declared in the custom signal file’s header, and they will be automatically indicated as inputs and initialized as part of the signal filter. When the enumerations are custom though, placing them in the header will prevent the file from being visible (or recognizable) in the MQL5 wizard, meaning you cannot do the wizard assembly. The work around this we have, for now, is omitting them from the custom signal class header but having the parameters and their assignment functions declared within the signal class, as is always the case with any input parameter. Once the wizard assembly is completed, we then make manual changes to the roster of input parameters and also the initialization of the signal class to add this custom enumeration parameters.