Better NN EA - page 7

[barnix]

Back Propagation NN example in msvc6

[[Deleted]]

Hi Barnix,

Thanks for your very interesting posts.

With the command line C program how are the results put into MT4 is an MQ4 file not required ?

Thanks

Lee

[barnix]

Invoke the program from Windows:

fx5.exe EURUSD240.csv > result.txt

CSV files exported from MT4.

leeb:
Hi Barnix,

Thanks for your very interesting posts.

With the command line C program how are the results put into MT4 is an MQ4 file not required ?

Thanks

Lee

[barnix]

Probabilistic NN (Classificaton, Bayesian NN) used by Better

[barnix]

Naive Bayesian Classifier (=> PNN used by Better)

The probabilistic neural network is a direct continuation of the work on Bayes classifiers.

[[Deleted]]

Thanks Barnix, I understand that bit but once we get the results how do we get metatrader to use them in forward testing ? Cheers

[oilfxpro]

Hi

I am posting Better's trades and Leeb's trade.They are both different and at different times .I hope Leeb does not mind

If any objections Leeb let me know and I will stop and remove your image

This will add fuel to discussion

OILFXPRO

[[Deleted]]

I don't mind you using the image, as you can see last nights trades and current ones are sells so it's not a buy only system. It is different to "betters" but his system got me thinking and is good to see someone doing so well with an EA

[oilfxpro]

leeb:
I don't mind you using the image, as you can see last nights trades and current ones are sells so it's not a buy only system. It is different to "betters" but his system got me thinking and is good to see someone doing so well with an EA

Leeb

You will be doing so well ,remember all your friends when you are trading from your Yacht

It is really great to see this thread and fresh air on this forum.This is how this forum should be

Keep it up guys.

OILFXPRO

[mikkom]

Craig:
All TA is curve fitting, future predictions based on patterns in the past. NNs are just another way of looking for these patterns.

Exactly my point. The problem with nn's is that to train them you have to understand the theory behind them very well.

ps. I would take a look at genetic programming if you are into this stuff, it's in some ways much cleaner than nn's and the information and algorithms gained with genetic algorithms can be used as part of your normal algorithms as well.

For more info see

Genetic programming - Wikipedia, the free encyclopedia

or read couple of Kozas books.