Step 12:  

Train the network and save the trained network in a file called digitnet

clear all;
close all;
clc;

[XTrain,YTrain] = digitTrain4DArrayData;
size(XTrain)      %images
size(YTrain)      %correct answer labels

XTrain=1-XTrain;  % Reverse the black and white colors.  Save and run the program to see the difference.

perm = randperm(size(XTrain,4),20);  % Randomize the order of images in XTrain
for i = 1:20
subplot(4,5,i);
imshow(XTrain(:,:,:,perm(i)));
end
 
layers = [
imageInputLayer([28 28 1])   
convolution2dLayer(3,8,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)

convolution2dLayer(3,16,'Padding','same')
batchNormalizationLayer
reluLayer
maxPooling2dLayer(2,'Stride',2)

convolution2dLayer(3,32,'Padding','same')
batchNormalizationLayer
reluLayer
averagePooling2dLayer(7)
 
fullyConnectedLayer(10)     % 10 output layer nodes
softmaxLayer
classificationLayer];  %close the bracket

options = trainingOptions('sgdm', ...
'InitialLearnRate',0.1, ...
'MaxEpochs',20, ...
'Verbose',false, ...
'Plots','training-progress', ...
'Shuffle','every-epoch' );

net1 = trainNetwork(XTrain,YTrain,layers,options);
save digitnet net1;

% XTrain is our training data (5000 images 28x28)
% YTrain is our correct answers (5000 labels)
% layers is the large array of layers we created above
% options is a variable that sets some of the training parameters

The network is now trained.  If you have a USB webcam, you can test it in the next step by writing digits on a paper to see if the network recognizes it.