- Dmytryi Voitukhov
- 버전: 1.54
- 업데이트됨: 23 7월 2021
UPD:https://t.me/mql5_neuroExt актуальная версия и обсуждение.
- for the successful created training bases I will provide an advisor for temporary use free of charge.
- training bases will be laid out as training progresses.
- training requires approximately 20 epochs.
At the first launch, the script creates the necessary files by itself.
Set TypeOfWork to Learn.
Because the Expert Advisor is resource-intensive and the market is unable to process it - the TypeOfWork parameter with the Market value has been introduced.
It must be switched to any other desired value!
Published for Collaborative Learning.
The depth of the set for the input data is 50 bars of the timeframe specified in the settings.
ThresholdOUT has no effect.
speed in some cases only affects very large values. In the training mode, open only 1 order with the minimum lot with equal SL and TP.
The schedule should be uniform. In this mode, the profit itself does not matter.
Distance only works for MaxOrders> 1.
MaxOrders> 1 slows things down a lot.
LearnEpoch is an unused parameter for looping optimization.
When the files data_w1_ [TF] _ [INSTRUMENT] .csv and data_w2_ [TF] _ [INSTRUMENT] .csv are deleted or the PeriodBars in the parameters are changed, the training will start from the beginning.
File location C: \ Users \ [USER] \ AppData \ Roaming \ MetaQuotes \ Terminal \ Common \ Neuro \