- The global minimum is achievable with a single hidden layer.
- With more hidden layers you add more local minima; most of which are higher than the global minimum.
Adding hidden layers to a patternnet hurts accuracy?
10 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Ekaterina Kryuchkova
le 3 Avr 2019
Modifié(e) : Greg Heath
le 4 Avr 2019
I am trying to use patternnet to classify the MNIST handwritten digit dataset.
I expected patternnet(10) to do worse than patternnet([10,10]), but it seems that the accuracy decreases as I add more layers.
Can someone explain why?
Here is my code:
images = loadMNISTImages('train-images.idx3-ubyte'); % initialize figure
labels = loadMNISTLabels('train-labels.idx1-ubyte'); % initialize figure
labels = labels'; % transpose
labels(labels==0)=10; % dummyvar function doesn´t take zeroes
labels=dummyvar(labels)';
net = patternnet([10,10]); %or patternnet(10)
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;
net.performFcn = 'crossentropy';
net = configure(net,images,labels);
net = train(net,images,labels);
y=net(images);
perf = perform(net,labels,y)
correctcount=0;
for i = 1:60000
[M, I]= max(y(:,i));
if t(I,i)== 1
correctcount=correctcount+1;
end
end
errorrate = 1- (correctcount/60000)
0 commentaires
Réponse acceptée
Greg Heath
le 3 Avr 2019
Modifié(e) : Greg Heath
le 4 Avr 2019
Thank you for formally accepting my answer
Greg
0 commentaires
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Classification dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!