MATLAB: How can i train a multilayer perceptron with complex data

artificial neural networkbackpropagation

Dear all,

i am interested in using a neural network classifier (i.e. MLP) for equalization of a quadrature amplitude modulation (QAM) signal.

the MATLAB toolbox does not support complex data as far as i understand… is there a way around this? i guess that i could simply split the data into real and imaginary parts and use two classfiers? However, this does not seem to be the ideal solution in my mind.

If someone can provide somebody can confirm in either direction whether it is possible to use a training method with a complex valued dataset i would appreciate it. Otherwise i think it is time to write my own network…

many thanks!

Best Answer

It can and has been done. Just use neural and complex in any search engine.

Although I tried it once or twice, I gave it up as a waste of time.

My solution was to double the number of inputs and outputs by using real and imaginary parts.

I am not familiar enough with the existing references to steer you in the right direction.

Beware and Good Luck.

Greg

Related Solutions

MATLAB: CNN seems to be too inaccurate to classify the images. Is there an alternative that I can explore

Alexnet is the simplest of the pretrained deep learning models, you might want to try others (resnet, inception, etc).

You might also not have enough images to get a good model, I don't know how many you have.

You might be experiencing overfitting, how went the training? A near 100% accuracy in training data with not that much in validation data would be a pretty strong indication of overfitting. You can avoid overfitting with image augmentation, dropout layers, etc.

Also, some problems have inherently ambiguous classes. A network to classify musical genders in song files might have a hard time in separating similar musical subgenders, for example. You might take some time to think if this is not your case. If it is, your network might not be "innacurate" at all, you problem is inherently difficult instead. The prediction class scores might give an idea of such ambiguities: 2 classes appearing with average-ish scores, indicating the image might belong to either.

MATLAB: Neural network accuracy improves on retraining without weight reinitialisation

A net with former weights will continue training from those weights.

If you wish to reinitialize to get an alternate design use the function configure at the top of the loop.

I have posted zillions of examples in both the NEWSGROUP (now only available in comp.soft-sys.matlab) and ANSWERS

Try searching

 greg configure

Hope this helps.

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: CNN seems to be too inaccurate to classify the images. Is there an alternative that I can explore

MATLAB: Neural network accuracy improves on retraining without weight reinitialisation

Related Question