Hi Yury Kulikov
0 - network learning is completed and learning result can be checked through the class variable: mse – learning error, epoch – number of accomplished learning cycles;
can you tell me 'mse – learning error ' general between witch interval ?? I test one and get the MSE=7.218702473434161e-008 ,is it all right ??
thank you very much!
Yurich:
MSE less is better. But one must bear in mind that a very small error value can indicate retraining network.
thaks very much. But i can't get a small error value , in the class "class_pnn" how did you exit leanning ? can let it calculate a long time to get a small error values?
qingyouwei:
... I test one and get the MSE=7.218702473434161e-008 ,is it all right ??
This is quite a small error.
Error and learning time depends on the prepared data for training. Preparing the data is a separate issue and it needs to explore before application of neural networks.
Nice. Even nicer that it works perfectly in MT4 too.
With a large number of samples the network does get rather large because it stores all the training samples. A useful addition would be a function to reduce the network by removing any samples that increase the total error.
Another useful addition would be the possibility of adding new training samples at a later date.
I'll contribute some code once I have figured out why I'm getting nan values for the mse from time to time.
Nice. Even nicer that it works perfectly in MT4 too.
With a large number of samples the network does get rather large because it stores all the training samples. A useful addition would be a function to reduce the network by removing any samples that increase the total error.
Another useful addition would be the possibility of adding new training samples at a later date.
I'll contribute some code once I have figured out why I'm getting nan values for the mse from time to time.
I also get mse = NaN time to time. This happens completely in random which is kind of strange. I will take a look at the code to see what could be the bug...
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use
PNN Neural Network Class:
Author: Yury Kulikov