Machine learning in trading: theory, models, practice and algo-trading - page 2299
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
It is funny - in Statistica package a block of neural networks like MPP(multilayer direct-directed perseptron) can not find the dependence of the type y = x1/x2.
During the search the package tried 600 networks, the best network showed less than 80% accuracy.
The number of hidden neurons is from 2 to 8.
It is funny - in Statistica package a block of neural networks like MPP(multilayer direct-directed perseptron) can not find the dependence of the type y = x1/x2.
During the search the package tried 600 networks, the best network showed less than 80% accuracy.
The number of hidden neurons is from 2 to 8.
Come on, don't be absurd... how many layers?
Come on, don't be ridiculous... how many layers?
3
It is funny - in Statistica package a block of neural networks like MPP(multilayer direct-directed perseptron) can not find the dependence of the type y = x1/x2.
During the search the package tried 600 networks, the best network showed less than 80% accuracy.
The number of hidden neurons is from 2 to 8.
https://www.mql5.com/ru/forum/8265/page3#comment_5706960
https://www.mql5.com/ru/forum/8265/page2#comment_333746
3
how many hidden layers ? )
how many hidden layers ? )
There are a total of 3 layers in each network.
In total there are 3 layers in each network.
So there's actually one hidden layer?
In total there are three layers in each network.
The input, the output, and the hidden one?
You actually have one hidden?
Yes