91av视频/亚洲h视频/操亚洲美女/外国一级黄色毛片 - 国产三级三级三级三级

  • 大小: 2.79MB
    文件類型: .rar
    金幣: 2
    下載: 0 次
    發(fā)布日期: 2023-10-28
  • 語言: Matlab
  • 標簽: RBM??

資源簡介

This is a small library that can train Restricted Boltzmann Machines, and also Deep Belief Networks of stacked RBM's. Train RBM's: %train an RBM with binary visible units and 500 binary hidden model= rbmBB(data, 500); %visualize the learned weights visualize(model.W); Do classification: model= rbmFit(data, 500, labels); prediction= rbmPredict(model, testdata); Train a Deep Belief Network with 500,500,2000 architecture for classification: models= dbnFit(data, [500 500 2000], labels); prediction= dbnPredict(models, testdata); see included example code for more I can be contacted on andrej.karpathy@ gmail. NOTE: This was a class project that I worked on for 1 month and then abandoned development for almost 4 years ago. Please do not send me specific questions about issues with the code or questions on how to do something. I only put this code online in hope that it can be useful to others but cannot fully support it. If you would like pointers to more actively maintained implementations, have a look here (https://github.com/rasmusbergpalm/DeepLearnToolbox) or maybe here (https://github.com/lisa-lab/DeepLearningTutorials) Sorry and best of luck! 原文：http://code.google.com/p/matrbm/

資源截圖

代碼片段和文件信息 

load?mnist_classify;

%%?Train?RBM?for?classification
%train?rbm?with?100?hidden?units
m=rbmFit（data100labels‘verbose‘true）;
yhat=rbmPredict（mtestdata）;

%print?error
fprintf（‘Classification?error?using?RBM?with?100?hiddens?is?%f\n‘?...
????sum（yhat~=testlabels）/length（yhat））;

%visualize?weights
figure（1）
visualize（m.W）;
title（‘learned?weights‘）;

%visualize?the?mislabeled?cases.?Note?the?transpose.?Visualize?assumes?DxN
%as?is?the?case?for?weights
figure（2）
visualize（data（yhat~=testlabels:）‘）;
title（‘classification?mistakes?for?RBM?with?100?hiddens‘）;
drawnow;

%%?Train?model?and?denoise?images
m2=?rbmBB（data100‘verbose‘true）;

%distort?100?images?around?by?setting?95%?to?random?noise
imgs=testdata（1:100:）;
b=rand（size（imgs））>0.95;
noised=imgs;
r=rand（size（imgs））;
noised（b）=r（b）;

%reconstruct?the?images?by?going?up?down?then?up?again?using?learned?model
up?=?rbmVtoH（m2?noised）;
down=?rbmHtoV（m2?up）;

%figure
z1=visualize（noised‘）;
z2=visualize（down‘）;

figure（3）
imshow（[z1?z2]）
title（‘denoising?95%?noise?with?RBM?with?100?hidden?units‘）;
drawnow;
%%?Train?a?DBN
op.verbose=true;
models=dbnFit（data[100?100]labelsopop）;
yhat2=dbnPredict（modelstestdata）;

%print?error
fprintf（‘Classification?error?using?DBN?with?100-100?hiddens?is?%f\n‘?...
????sum（yhat2~=testlabels）/length（yhat2））;

%visualize?weights
figure（4）
subplot（121）
visualize（models{1}.W）;
title（‘learned?weights?on?DBN?layer?1‘）;
subplot（122）
visualize（models{2}.W）;
title（‘learned?weights?on?DBN?layer?2‘）;

%visualize?the?mislabeled?cases.?Note?the?transpose.?Visualize?assumes?DxN
%as?is?the?case?for?weights
figure（5）
visualize（data（yhat2~=testlabels:）‘）;
title（‘classification?mistakes?for?DBN?with?100-100?hiddens‘）;

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件???????1796??2010-10-31?13:00??RBMLIB\examplecode.m

?????文件????2974337??2010-10-31?13:00??RBMLIB\mnist_classify.mat

?????文件???????1577??2010-10-31?13:01??RBMLIB\RBM\dbnFit.m

?????文件????????495??2010-10-31?13:01??RBMLIB\RBM\dbnPredict.m

?????文件????????409??2010-10-31?13:01??RBMLIB\RBM\interweave.m

?????文件?????????65??2010-10-31?13:01??RBMLIB\RBM\logistic.m

?????文件????????977??2010-10-31?13:01??RBMLIB\RBM\nunique.m

?????文件????????690??2010-10-31?13:01??RBMLIB\RBM\prepareArgs.m

?????文件???????3819??2010-10-31?13:01??RBMLIB\RBM\process_options.m

?????文件???????5217??2010-10-31?13:01??RBMLIB\RBM\rbmBB.m

?????文件???????6147??2010-10-31?13:16??RBMLIB\RBM\rbmFit.m

?????文件????????358??2010-10-31?13:01??RBMLIB\RBM\rbmHtoV.m

?????文件????????877??2010-10-31?13:22??RBMLIB\RBM\rbmPredict.m

?????文件????????355??2010-10-31?13:01??RBMLIB\RBM\rbmVtoH.m

?????文件????????286??2010-10-31?13:01??RBMLIB\RBM\softmaxPmtk.m

?????文件????????371??2010-10-31?13:01??RBMLIB\RBM\softmax_sample.m

?????文件????????750??2010-10-31?13:01??RBMLIB\RBM\visualize.m

?????文件??????13554??2015-03-23?21:12??RBMLIB\readme.docx

?????目錄??????????0??2015-03-23?21:10??RBMLIB\RBM

?????目錄??????????0??2015-03-23?21:12??RBMLIB

-----------?---------??----------?-----??----

??????????????3012080????????????????????20


評論

共有 條評論