Neural Network toolbox - transferFcn and transferParam
24 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Francisco
am 1 Feb. 2011
Bearbeitet: Guru
am 4 Dez. 2014
I am trying to define a transfer function with parameters in the Neural network toolbox but I am not able to define the parameters correctly
What I did?
1. I copied the LOGSIG Logarithmic sigmoid transfer function file -my transfer function includes a factor in the exponent
2. I defined the parameter to receive as a real scalar with default value 1.0
function param = parameters, param = ...
[nnetParamInfo( 'alpha', ...
'alpha factor in the exponent', ...
'nntype.real_scalar', ...
1.0, ...
'alpha factor in the exponent')];
end
3. I include it in the 'apply' and 'da_dn' functions
function a = apply(n,param)
% The same as logsig but with alpha factor in the exponent
a = 1 ./ (1 + exp(-n * param.alpha));
i = find(~isfinite(a));
a(i) = sign(n(i));
end
4. I create the network and establish the alpha parameter
net = feedforwardnet([10, 10]);
% ... more initializations ...
net.layers{1}.transferParam.alpha = 1.1;
The LAST LINE raise this ERROR
??? Error using ==> param
Too many input arguments.
Error in ==> network.subsasgn>setLayerTransferParam at 1214
err = nntest.param(functionInfo.parameters,transferParam, ...
Any ideas? I did not find any good documentation / example about how to define a transfer function with parameters
4 Kommentare
Greg Heath
am 4 Dez. 2014
There is no problem worth talking about!!!
.. . Read my answer
Greg
Guru
am 4 Dez. 2014
Bearbeitet: Guru
am 4 Dez. 2014
Actually I don't want to train the network. I'm not using any training algorithms. Instead I'm varying the control parameter of the custom transfer function that I've written. My network is not exactly for the functionality traditionally used with neural networks. So I need to initialise this parameter for the transfer function and vary it based on the output.
This is what the error I'm runnign into,
Undefined function or variable 'newSize'.
Error in network/subsasgn>setLayerTransferParam (line 1231) net.layers{i}.range = repmat(feval(net.layers{i}.transferFcn, ...
Error in network/subsasgn>network_subsasgn (line 189) if isempty(err), [net,err] = setLayerTransferParam(net,i,transferParams); end
Error in network/subsasgn (line 13) net = network_subsasgn(net,subscripts,v,netname);
Error in TestNet (line 21) net.layers{1}.transferParam.no_of_iter = 4;
Akzeptierte Antwort
George Evers
am 2 Feb. 2011
Francisco,
Have you tried the solution methods suggested at http://www.mathworks.com/support/solutions/en/data/1-17LOK/index.html?product=NN&solution=1-17LOK ?
George
3 Kommentare
George Evers
am 3 Feb. 2011
I don't have the NN toolbox by which to help with the debbugging. If no one else has the answer, you might just click "Please provide feedback to help us improve this Solution" at the link above and request the desired instructions.
Weitere Antworten (1)
Greg Heath
am 9 Feb. 2013
There is absolutely no reason to use parameters in the transfer function.
Training will vary the weights to minimize the error.
If you want to decrease training time , just increase the learning rate
Hope this helps.
Greg
0 Kommentare
Siehe auch
Kategorien
Mehr zu Sequence and Numeric Feature Data Workflows finden Sie in Help Center und File Exchange
Produkte
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!