neural network and inputs - 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
I still don't understand what you want as an output?
Why don't you first define what you want in the OUTPUT? And then go through the inputs.
The two main problems are solved by different machine learning methods: classification and regression.
Neural networks are not currently the best method for these tasks, although if prepared correctly they do the job.
Reference vector machines (SVMs), RandomForest, decision trees and many others are more suitable.
And the distinction between clustering and classification has almost been erased since the introduction of the concept and methods of "partial learning".
It is time to climb out of the NS cellar. The horizon of methods is vast.
Good luck
More adaptable support vector machines (SVMs), RandomForest, decision trees
There she is - the superman's neuron! :-)
Mr. Batter - three hundred quid! The years are minuscule... AND IT'S A NEURON EXPERT!!!
More adaptable support vector machines (SVMs), RandomForest, decision trees and many others.
Actually the analysis of markets, making trading decisions, as paradoxical and strange as it may seem to some, is a very simple task. The whole question-problem is the inflated expectations of the "trader". And you are right:
Neural networks ... when properly prepared, do the job.
And with the result which will not differ fundamentally from any of the listed methods, and in general from any nonempty methods.
There she is - the superman's neuron! :-)
Mr. Batter - three hundred quid! The years are minuscule... AND IT'S A NEURON EXPERT!!!
And here are those "inflated expectations" I mentioned just above, 25% p.a., for only $300 and laughter in the audience.