Matlab示例代碼為兩部分，分別對應不同的論文：
1.?Reducing?the?Dimensionality?of?data?with?neural?networks?
　　ministdeepauto.m???backprop.m???rbmhidlinear.m
2.?A?fast?learing?algorithm?for?deep?belief?net
　　mnistclassify.m?　　backpropclassfy.m??
?其余部分代碼通用。
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
														mnistclassify.m
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
clear?all
close?all
maxepoch=50;????%迭代次數
numhid=500;?numpen=500;?numpen2=2000;?
fprintf（1‘Converting?Raw?files?into?Matlab?format?\n‘）;
converter;??
fprintf（1‘Pretraining?a?deep?autoencoder.?\n‘）;
fprintf（1‘The?Science?paper?used?50?epochs.?This?uses?%3i?\n‘?maxepoch）;
makebatches;%分批數據?
[numcases?numdims?numbatches]=size（batchdata）;?%獲取batchdata數據大小
%%numcases??每批數據的個數
%%numdims???數據元組的維度
%%numbtches?數據批數
fprintf（1‘Pretraining?layer?1?with?RBM:?%d-%d?\n‘numdimsnumhid）;%圖像輸入層到第一個隱藏層
restart=1;??????????????????%設置初始化參數
rbm;????????????????%調用RBM訓練數據?
hidrecbiases=hidbiases;??%獲取隱藏層偏置值
save?mnistvhclassify?vishid?hidrecbiases?visbiases;?%
fprintf（1‘\nPretraining?layer?2?with?RBM:?%d-%d?\n‘numhidnumpen）;%第一個隱藏層到第二個隱藏層
batchdata=batchposhidprobs;?????%上一個RBM的隱藏層輸出，讀入作為這個RBM的輸入
numhid=numpen;%設置隱藏層的節點數，輸入的節點數已經由讀入數據給出
restart=1;
rbm;
hidpen=vishid;?penrecbiases=hidbiases;?hidgenbiases=visbiases;?%同上，提取權值，偏置，
save?mnisthpclassify?hidpen?penrecbiases?hidgenbiases;
fprintf（1‘\nPretraining?layer?3?with?RBM:?%d-%d?\n‘numpennumpen2）;%第二個隱藏層到第三層隱藏層，其余同上
batchdata=batchposhidprobs;
numhid=numpen2;
restart=1;
rbm;
hidpen2=vishid;?penrecbiases2=hidbiases;?hidgenbiases2=visbiases;
save?mnisthp2classify?hidpen2?penrecbiases2?hidgenbiases2;
backpropclassify;?
?

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
														backpropclassify.m
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
maxepoch=200;
fprintf（1‘\nTraining?discriminative?model?on?MNIST?by?minimizing?cross?entropy?error.?\n‘）;%最小化交叉熵
fprintf（1‘60?batches?of?1000?cases?each.?\n‘）;
load?mnistvhclassify%加載各層之間的權值，以及偏置
load?mnisthpclassify
load?mnisthp2classify
makebatches;%分批數據
[numcases?numdims?numbatches]=size（batchdata）;
N=numcases;?%獲取每批數據向量數
%%%%?PREINITIALIZE?WEIGHTS?OF?THE?DISCRIMINATIVE?MODEL%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
w1=[vishid;?hidrecbiases];%第一層到第二層的權重，以及第二層的偏置
w2=[hidpen;?penrecbiases];%類上
w3=[hidpen2;?penrecbiases2];%類上
w_class?=?0.1*randn（size（w32）+110）;%隨機生成第四層列數+1行，10列的矩陣
?
%%%%%%%%%%?END?OF?PREINITIALIZATIO?OF?WEIGHTS??%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
l1=size（w11）-1;%獲取每層的單元個數
l2=size（w21）-1;
l3=size（w31）-1;
l4=size（w_class1）-1;%最高層的單元個數
l5=10;?%label層單元個數
test_err=[];%
train_err=[];%

for?epoch?=?1:maxepoch
%%%%%%%%%%%%%%%%%%%%?COMPUTE?TRAINING?MISCLASSIFICATION?ERROR?%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
err=0;?
err_cr=0;
counter=0;
[numcases?numdims?numbatches]=size（batchdata）;
%%numcases??每批數據的