MATLAB: Neural Network Tool Box

Deep Learning Toolboxneural networks

I am working on a classification problem and the codes are written in m files. I am calling net=newff(….) within the m file.Once the network is trained, How to save the net? How to access the net weights?

Best Answer

What version are you using? We recommend using feedforwardnet.

If you run the example from the doc for feedforwardnet, you can access the net weights:

net.InputWeights
net.LayerWeights

And it can be saved to a *.mat file the same way you save any variable.

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

 Use the command window
 help mse
 doc mse

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: Neural Net: Saving Trained Net

I am not sure why you used a cascade forward net. That net has no feedack loops.

The generating equations indicate that a narxnet is more appropriate.

Is u(k)+ *0.3*u(k) a misprint? Should the latter be u(k-1)?

When you change to a narxnet, check the significant values (>0.21) of the crosscorrelation function nncorr(U,Y,N-1)and the autocorrelation function nncorr(Y,Y,N-1) to determine good values for the delays. The capitals indicate zscore transformations (i.e., U = zscore(u), etc).

Also change the divide function from dividerand (destroys u-y and y-y correlations) to either 'divideblock' or another choice.

As for your CFnet, you have 2 hidden layers with 30 nodes resulting in Nw = (1+1)*20+(20+1)*10+(10+1)*1 = 261 weights. A narxnet will probably need fewer hidden nodes and weights.