NEURAL NETWORK reproducibility of results using neural networks without initfcn = 'rands'
2 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Flo Trentini
el 23 de Nov. de 2011
Editada: faramarz sa
el 22 de Oct. de 2013
I don't understand why each time I train my network I obtain different results. I create neural network with newff function.
net = newff(input,target,3);
i set the init funciton equal to 'initzero' as below
net.inputweights{1,1}.initfcn = 'initzero';
net.layerWeights{1,2}.initFcn = 'initzero';
net.biases{1}.initFcn = 'initzero';
net.biases{2}.initFcn = 'initzero';
then I initialize the network and train it
net = init(net);
net = train(net,input,target);
And yet each run gives me different results ! How is that possible ? Where is the random hidden ?
PS: I'm using 'trainbr' as trainFctn
net.trainFcn = 'trainbr';
0 comentarios
Respuesta aceptada
Greg Heath
el 27 de Oct. de 2012
The answer is 'dividerand' randomizes the order of the input/target pairs.
Hope this helps.
Thank you for formally accepting my answer.
Greg
0 comentarios
Más respuestas (4)
faramarz sa
el 22 de Oct. de 2013
Editada: faramarz sa
el 22 de Oct. de 2013
Different Matlab Neural networks toolbox results is because of two reasons: 1-random data division 2-random weight initialization
For different data division problem use function "divideblock" or "divideint" instead of "dividerand" like this:
net.dividefcn='divideblock;
net.divideparam.trainratio=.7;
net.divideparam.valratio=.15;
net.divideparam.testratio=.15;
For random weight initialization problem, It seems (I'm not sure) all Matlab initialization functions ("initzero", "initlay”, "initwb”, “initnw”) are almost random. So you should force this functions produce similar results per call.
RandStream.setGlobalStream (RandStream ('mrg32k3a','Seed', 1234));
And then use one of them:
net.initFcn='initlay';
net.layers{i}.initFcn='initnw';
0 comentarios
Greg Heath
el 26 de Nov. de 2011
I don't know.
Avoid the issue by intializing rand before calling newff. Then just accept the resulting default initnw weights automatically provided by newff.
Hope this helps (at least you will get reproducible results!).
Greg
0 comentarios
Greg Heath
el 3 de Dic. de 2011
Try printing out the weights just before the call to TRAIN to see if they are different. Don't forget to initialize RAND before calling NEWFF.
Hope this helps.
Greg
Greg Heath
el 5 de Dic. de 2011
Weight space contains jillions of local minima. Therefore I never expect to get a good solution the first time around. That is why I usually use a double loop over (outer) number of hidden nodes and (inner) multiple random weight initializations (Typically for i=1:10; for j=1:10; ...).
Sometimes I have to repeat this several times. Try searching the newsgroup using
heath newff Ntrials
Hope this helps.
Greg
P.S. How many good solutions of the XOR problem do you get for H = 1:5; Ntrials = 1:10?
0 comentarios
Ver también
Productos
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!