Machine learning in trading: theory, models, practice and algo-trading - page 2748
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
On topic)
Please note that from build 3440 we start distributing AVX versions of the software: https://www.mql5.com/ru/forum/432624/page5#comment_42117241.
The next step is to rewrite the mathematical apparatus to vector and OpenCL functions, which gives ten-tract accelerations without the need to install additional libraries like CUDA.
And if the processor doesn't have AVX instructions, then it won't work, or is it about something else?
You know, I would really like not only OpenCL, but a simple possibility - to give local agents access to data in memory, making them shared, at least for reading - this is very important for large samples - now each agent duplicates a file with data in memory, which often leads to the fact that the cores are idle.
This is due to the imposition of western "science" for the bulls for the last 50+ years. They say that in maths it started with Kolmogorov, I think. In theoretical physics with all these warps of space-time there is nothing from reality and common sense for a long time. It's more like divorce than physics. And Einstein is a crook :)
You've watched Katshchik, now you're relaying his thoughts as your own, word for word))))))
.
Katushik is relaying my thoughts, and I gave you the link.
You're really sick, not everyone can lie like that.... I'm amazed, honestly.
I mean, am I an authority to anyone? Why so much attention to my person?
I provided a link to a reference I made to Katrzyk from '17. Prove me wrong.I provided a link to my reference to Katrzyk, from '17. Prove me wrong.
Where is she
in the previous post
#299
I don't argue with training on every bar, and maybe even on a non stationary tick for example. I don't understand the training structure completely. Is EA logic a separate training or part of the training on each bar? It is like the tails of the first training, how many tails, or stages of training?
I do not pretend to be true, but it is most likely the stage of Interpretation of training results and adjusting to money-management of a particular trade and, perhaps, even a particular asset... and answers to questions
It's slipped in here above that the value of even a correct prediction can be zero.
To me, the value of a prediction depends not only on the probability of error, but on the teacher himself.
- Is the teacher predicting the next bar or the trend?
- What time period is the prediction being made and what time period are we trading on?
- What target profit does our teacher predict?
- What is the relationship between the teacher and the spread?
A lot of questions that have not been discussed here.
also probably make their contribution already at the stage of a trading EA... after all, after fs and training, the target obtained can be used as a basis for decision-making OR rejected (for the reasons mentioned in the quote or other)... although these reasons can be taken into account in the training... but money-management and risk-management can also be included in the Expert Advisor, so as not to overload the model....
although the question, of course, was not for me... but Interpretation of training results is also an important task
Vladimir's articles also have an error around 10-20%, but the balance line is not encouraging.
this may also depend on the Interpretation "a-post" of the training....