Machine learning in trading: theory, models, practice and algo-trading - page 1818
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
I came across an interesting picture. To talk about "patterns", the current situation, the perspective, and for a better understanding of the "task" So, if you want a "neural network" to be able to help at least earn something, it "must" be able to "understand the situation" and recognize a Jeep here, having learned "on history". I do not know how, honestly, I myself am curious :))) Maybe a program capable of this will be the AI. A "natural" neural network can do the same thing.
Do you store patterns as a knowledge base, or do you search every time after a candle closes?
I came across an interesting picture. To talk about "patterns", the current situation, the perspective, and for a better understanding of the "task" So, if you want a "neural network" to be able to help at least earn something, it "must" be able to "understand the situation" and recognize a Jeep here, having learned "from history". I do not know how, honestly, I myself am interested :))) Maybe a program capable of this will be the AI. The "natural" neural network has the same way it works.
Task - "is there a jeep in the picture"
The correct answer is NO jeep!
If you see it, then you are either able to see through the swamp, or you have schizophrenia.
I understand that when the brain sees the roof of the jeep it realizes that it is somewhere down in the swamp, but the question is "is there a jeep in the picture" in the picture there is no jeep, it is under the swamp.
It's like showing a network a picture of a field and making it say it sees a gopher, we know it's there for sure, but the picture is a field!!!
You've got to think bigger, gentlemen...
The task is "is there a Jeep in the picture?
...
you need to think more, gentlemen...In the area of the triple dot - I think there are even two of them :)
Do you store patterns as a knowledge base, or do you look for them again each time a candle closes?
This 4-digit number is the pattern code. It is important for machine processing of price information. Using this code, I can easily draw the price picture even without seeing it. The number of patterns is limited. They change with time, and knowing the current pattern, it is easy to predict the next one.
I don't have to save them into the database. The program takes the current code and works with it.
===========
That's the sad thing about Jeep. To reproduce it programmatically is probably not realistic. Our brains can do it with our imagination, but programmatically it's unlikely.
On the other hand, the price is easier, it is all visible and its behavior is predictable. (partly))
This 4-digit number is the pattern code. It is important for machine processing of price information. Using this code, without any problems, I can draw a picture of the price even without seeing it. The number of patterns is limited. They change with time, and knowing the current pattern, it is easy to predict the next one.
I don't have to save them into the database. The program takes the current code and works with it.
Little understood, but interesting )) I can see that you are a man with ideas, it's cool! If I can help you with machine learning, feel free to contact me.
With jeep sadly. I don't think it's realistic to reproduce it software. Our brains can draw it with our imagination, but software is unlikely.
On the other hand, it is easier with the price - it is all visible and its behavior is predictable. (Partly))
That's not the point, you can do it ALL ))
The point is that the task itself is not set correctly and do not even realize it, and they want the result ...
It's like with code - there is no bad code, there is a bad programmer, if the code is written incorrectly and doesn't work, it's not a problem of code (the code can't work incorrectly, it works exactly as it was written), but the problem of a careless programmer. Exactly the same is with the NS, and with the Jeep.
Who has useful information about sampling methods?
It is desirable to have comparative specifications
as an example:https://www.healthknowledge.org.uk/public-health-textbook/research-methods/1a-epidemiology/methods-of-sampling-population
Who has useful information about sampling methods?
It is desirable to have comparative specifications
as an example:https://www.healthknowledge.org.uk/public-health-textbook/research-methods/1a-epidemiology/methods-of-sampling-population
There should be a lot of papers on social studies, psychologists write them on the diploma. But the math is usually tight there.
Usually it's too topical stuff likehttps://helpiks.org/7-16586.html
What do you want to separate/select?
There should be a lot of papers on social studies, psychologists write them on their diplomas. But there's usually not much math there.
Usually it's too thematic stuff likehttps://helpiks.org/7-16586.html
What do you want to divide/select?
Yeah, it's all the same theme, randomly searching for predictor-target dependencies
The trades are opened randomly, then into a neural network. A lot depends on competent sampling
For example, with this I found the dependencies between TFs, as you suggested
Thanks, I will take a look at it.