Adding hidden layers to a patternnet hurts accuracy?

7 views (last 30 days)
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
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);
perf = perform(net,labels,y)
for i = 1:60000
[M, I]= max(y(:,i));
if t(I,i)== 1
errorrate = 1- (correctcount/60000)

Accepted Answer

Greg Heath
Greg Heath on 3 Apr 2019
Edited: Greg Heath on 4 Apr 2019
  1. The global minimum is achievable with a single hidden layer.
  2. With more hidden layers you add more local minima; most of which are higher than the global minimum.
Thank you for formally accepting my answer

More Answers (0)

Community Treasure Hunt

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

Start Hunting!