Step 10:  

Add a softmax and a categorization layer.  No need to specify any new parameters for them.  Remember to close the square bracket to complete the layers structure.  

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

At this point the structure of your deep network (CNN) has been fully defined.  
In the next step, we'll just make some additions and minor modifications.