Using neural networks in trading - page 34
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
Take the classical case of the plane. The theory states that the data (in the case of the plane) must be linearly separable in order to produce a successful classification.
The plane is a classical example, not a classical case. And this simple separability is used in such examples purely to illustrate the idea.
It is necessary to gradually increase the dimensionality of the feature vector in order to construct a practically acceptable classification. The separation of classes will inevitably be non-linear.
Well, yes, an example, not a case. Plus a picture to clearly illustrate. Thank you for the correction.
I agree in principle with the increase in dimensionality. It would be certain that this increase would have an effect. But I'm afraid we'll get the same mess, only in n-dimensional space?
Collapse of ideas + creative local minimum...
Nice article from MQ themselves about classification. Three dimensional vectors and everything works. Amazing... https://www.mql5.com/ru/articles/283
Take the classical case of the plane. The theory states that the data (in the case of the plane) must be linearly separable in order to produce a successful classification.
Bullshit.
Bribes with simplicity and brevity. Couldn't the sentence be expanded somewhat informatively?
It's a nice touch of simplicity and brevity. Could you informatively expand the sentence a bit?
The first classical test of a classification grid is XOR. It is linearly non-divisible and just flat.
Nice! Then one more question. If you don't mind, please describe what is meant by "a classification grid" in this example. I.e. what is the architecture of the network, for example?
The picture - spite the econometrics ))))) You're making a big deal out of it. I have a suspicion that no one is trading, but just to argue who is smarter ))))
The picture - spite the econometrics ))))) You're making a big deal out of it. I have a suspicion that no one trades, but just to argue who is smarter ))))
What is this picture about? What are these signals? Is it a forward test or on history? .....?
ZS. Why do you have to do something out of spite? Maybe write "for the good of what"?
What is the picture about? What are the signals? Is it a forward test or on history? .....?
ZS. Why do you have to do something out of spite? Maybe write "for the good of what"?
What's the picture about? ....
How can I say...
I'm afraid to even say - Using neural networks in trading. I may be mistaken, but that's the title of the subject.
What are those signals? It's hard to guess.
And this is the most real time. ))))
p.s. Just kidding ))) Goodness gracious ))) do not take it so personally.
What's the picture about? ....
How can I put it...
I'm afraid to even say - Using neural networks in trading. I may be wrong, but that's the title of the topic .
What are those signals? It's hard to guess.
And this is the most real time. ))))
p.s. Just kidding ))) geez ))) don't take it so personally.
I'm sorry, I'm not capable of maintaining a conversation in that tone of voice.
Absolutely agree !
Nothing. There will be less happiness. So to each his own. Don't worry.