how can i changhe the transfer function of output layer of neural network?

i want to change the transfer function of output layer from purelin(difult) to other function like hardlim. i khow that i could use "net.layers{1}.transferFcn='tansig'" for layers but how could change the output?

Answer 1

[Greg Heath]

With obsolete (since 2010b) nets like newfit for regression/curve-fitting and newpr for classification/pattern-recognition (both call newff), you can specify the transfer functions in the net creation statement. See

   help newfit , help newpr

However, in their replacements fitnet and patternnet (both call feedforwardnet), you have to specify them as you have indicated. The default configurations are 2 layer nets with layer 2 containing the output transfer function.

I do not recommend using non-differentiable functions like hardlim and hardlims.

For best performance use scaled centered inputs via mapminmax, mapstd or zscore. The corresponding compatible hidden layer transfer function is the symmetric TANSIG (i.e., I do not recommend LOGSIG for hidden layers).

For fitnet, also use scaled centered outputs with PURELIN or TANSIG as output transfer functions.

For patternnet, outputs are desired to be consistent estimates of the input conditional class posterior probabilities. Therefore targets should be unit column vectors with the "1" in the row corresponding to the true class of the corresponding input. The corresponding output transfer function is LOGSIG.

   help ind2vec , help vec2ind

   net.layers{2}.transferFcn = 'logsig'

Hope this helps.

Thank you for formally accepting my answer

Greg

[mehdi]

thanks alot

[Christina Sivoronov]

Is it possible to have a simmilar approach for the hyperbolic tangent function ('tanh'). This approach seems to throw an error whilst doing so.

Answer 2

[Hesam Jafarian]

with NET.layers you can access to the network layers' property where you can set the transfer function layer {i} by using the following command :

net.layers{i}.transferFcn = 'something' ex: net.layers{1}.transferFcn = 'logsig'

note: for other networks not obsolete it works too for instance (fitnet)