weird plotregression plots for a 10% of my fitnet neural networks

1 view (last 30 days)
Dear comunity,
i trained a fitnet with a inputmatrix (7x2118 double) and a targetvector (1x2118 double) like this:
hiddenLayerSize = [105 15];
trainFcn = 'trainlm';
net = fitnet(hiddenLayerSize,trainFcn);
for netI=1:100
[TrainedNet(netI).net,trainRecords(netI).tr] = train(net,inputmatrix,targetvector);
end
for 9 of my 100 ANNs i got a really strange result in the training.
Have you ever seen this kind of strips within a network output? Why dos it happen? What could be an explanation?
Kind regards, MLP

Answers (1)

Greg Heath
Greg Heath on 18 Jan 2020
Sometimes training gets into a parameter space rut. That is why it is wise to train multiple models.
Hope this helps.
Greg
THANK YOU FOR FORMALLY ACCEPTING MY ANSWER
Greg

Categories

Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!