Searching for an arbitrary pattern using a neural network - page 9
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
...but based on what probability criterion of correlation...
Hanging...
A neural network can be trained to classify and catalogue images, but on the basis of what criterion of probability of correlation of this or that image to a certain category of the catalogue it will happen, that is the probable error of any neural network.
Already memorized images with time will come to screening out with worsening results of reaction on them, thus success of any neural network will consist of a momentary content of that very catalogue of images on its memory, which are effective at that very second. Its extended base would be a minus rather than a plus.
When you have some substance in your statements, then I will seek it out. Just because you can't understand something doesn't mean it's heresy.
And where you have gone - it is very well seen - what wild conclusions.
Well then, all I have to do is invite you and your friends in the MoD area to my live broadcast, which I plan to hold at least until the new year. There will be an early warning in the machine learning thread. I think one broadcast will be enough for you to form an opinion on the essence of my words.
Already imagined...
Already imagined...
Only dead people and fools don't change their minds.
"... First ask yourself how I can use the response from the NS? Does it need to be transformed to make a decision, etc. And only then you will understand that it's not the pattern itself which is important, but the reaction of the market to its appearance. And this is the reaction to trade.
The market does not react to a pattern, which is a kind of indicator, an indicator of the market. Sort of like a waving ball to which the market does not react, but it does willingly.
What response from NS do you mean - I do not understand. First formulate the problem: how do you recognise a pattern?
You have already been told that the NS does not recognise patterns, which simple mathematics does a priori. what is a pattern? it is a description of the conditions of its formation, which can easily be solved by mathematics. The search for a pattern that is not known cannot be either because we do not know what to look for. So the NS does not need to recognize patterns, it needs to recognize the future market reaction to this pattern.
Blonde! I can feel it in my spine.
Blonde! I can feel it in my spine.
This is the kind of thing I am interested in.
Essentially, the most profitable thing would be to define just two states: trend and flat, as I don't see the usefulness of patterns yet.
Is it possible to break the chart into at least these two states?