资源简介
DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容

代码片段和文件信息
% Version 1.000
%
% Code provided by Ruslan Salakhutdinov and Geoff Hinton
%
% Permission is granted for anyone to copy use modify or distribute this
% program and accompanying programs and documents for any purpose provided
% this copyright notice is retained and prominently displayed along with
% a note saying that the original programs are available from our
% web page.
% The programs and documents are distributed without any warranty express or
% implied. As the programs were written for research purposes only they have
% not been tested to the degree that would be advisable in any important
% application. All use of these programs is entirely at the user‘s own risk.
% This program fine-tunes an autoencoder with backpropagation.
% Weights of the autoencoder are going to be saved in mnist_weights.mat
% and trainig and test reconstruction errors in mnist_error.mat
% You can also set maxepoch default value is 200 as in our paper.
maxepoch=200;
fprintf(1‘\nTraining discriminative model on MNIST by minimizing cross entropy error. \n‘);
fprintf(1‘60 batches of 1000 cases each. \n‘);
load mnistvhclassify
load mnisthpclassify
load mnisthp2classify
makebatches;
[numcases numdims numbatches]=size(batchdata);
N=numcases;
%%%% PREINITIALIZE WEIGHTS OF THE DISCRIMINATIVE MODEL%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
w1=[vishid; hidrecbiases];
w2=[hidpen; penrecbiases];
w3=[hidpen2; penrecbiases2];
w_class = 0.1*randn(size(w32)+110);
%%%%%%%%%% END OF PREINITIALIZATIO OF WEIGHTS %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
l1=size(w11)-1;
l2=size(w21)-1;
l3=size(w31)-1;
l4=size(w_class1)-1;
l5=10;
test_err=[];
train_err=[];
for epoch = 1:maxepoch
%%%%%%%%%%%%%%%%%%%% COMPUTE TRAINING MISCLASSIFICATION ERROR %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
err=0;
err_cr=0;
counter=0;
[numcases numdims numbatches]=size(batchdata);
N=numcases;
for batch = 1:numbatches
data = [batchdata(::batch)];
target = [batchtargets(::batch)];
data = [data ones(N1)];
w1probs = 1./(1 + exp(-data*w1)); w1probs = [w1probs ones(N1)];
w2probs = 1./(1 + exp(-w1probs*w2)); w2probs = [w2probs ones(N1)];
w3probs = 1./(1 + exp(-w2probs*w3)); w3probs = [w3probs ones(N1)];
targetout = exp(w3probs*w_class);%?
targetout = targetout./repmat(sum(targetout2)110);%?
[I J]=max(targetout[]2);
[I1 J1]=max(target[]2);
counter=counter+length(find(J==J1));
err_cr = err_cr- sum(sum( target(:1:end).*log(targetout))) ;%?
end
train_err(epoch)=(numcases*numbatches-counter);
train_crerr(epoch)=err_cr/numbatches;
%%%%%%%%%%%%%% END OF COMPUTING TRAINING MISCLASSIFICATION ERROR %%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%% COMPUTE TEST MISCLASSIFICATION ERROR %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
err=0;
err_cr=0;
counter=0;
[testnumcases testnumdims testnumbatches]=size(testbatchdata);
N=testnumcases;
for batch = 1:testnumbatches
data = [testbatchdata(::batch)];
target = [testbatchtargets(::batch)];
data = [data ones(N1)
属性 大小 日期 时间 名称
----------- --------- ---------- ----- ----
目录 0 2014-09-21 11:25 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\
文件 5483 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\backpropclassify.m
文件 904 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\bp.asv
文件 935 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\bp.m
文件 2001 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\dbnFit.m
文件 495 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\dbnPredict.m
文件 1799 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\examplecode.m
文件 409 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\interweave.m
文件 65 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\logistic.m
文件 977 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\nunique.m
文件 690 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\prepareArgs.m
文件 3819 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\process_options.m
文件 5293 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\rbmBB.m
文件 6149 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\rbmFit.m
文件 3806 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\rbmGB.m
文件 358 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\rbmHtoV.m
文件 877 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\rbmPredict.m
文件 355 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\rbmVtoH.m
文件 286 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\softmaxPmtk.m
文件 371 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\softmax_sample.m
文件 976 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\train.asv
文件 913 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\train.m
文件 3205929 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\traindata.mat
文件 750 2014-09-21 11:22 DBN源码,深度学习领域的适合初学者学习的代码之一,基础必备的内容\visualize.m
- 上一篇:软件构件与中间件技术
- 下一篇:地形渲染的动态LOD四叉树算法
相关资源
- 编程实现二维DCT变换
- 图像二值化
- 用FFT对信号进行频谱分析
- Tone-Reservation
- QGA 量子遗传算法
- 差分形式的阻滞增长模型
- 遗传算法的M文件
- 广联达6.0写锁包,2020年11月最新
- 简单二阶互联系统的非线性动力学分
- 机器学习个人笔记完整版v5.2-A4打印版
- 深度学习卷积神经网络可检测和分类
- GAN对抗式生成网络的应用:从图片上
- [en]深度学习[Deep Learning: Adaptive Compu
- 李宏毅-机器学习(视频2017完整)
- 吴恩达深度学习第一课第四周作业及
- 手写数字识别-模板匹配法
- 机器学习深度学习 PPT
- 麻省理工:深度学习介绍PPT-1
- Stock_Watson_动态因子分析模型
- 果蝇优化算法优化支持向量回归程序
- 自己做的一个简单GUI扑克纸牌识别-
- multi output SVR
- Wikipedia机器学习迷你电子书之四《D
- AR过程的线性建模过程与各种功率谱估
- 深度学习在遥感中的应用综述
- 深度学习数据集标注
- PCNN TOOLBOX
- plstoolbox.zip
- 深度学习算法实践源码-吴岸城
- 中国国家基础地理信息系统GIS数据
评论
共有 条评论