深度学习工具包 DeepLearningToolbox

深度学习工具包 Deprecation notice. ----- This toolbox is outdated and no longer maintained. There are much better tools available for deep learning than this toolbox, e.g. [Theano](http://deeplearning.net/software/theano/), [torch](http://torch.ch/) or [tensorflow](http://www.tensorflow.org/) I would suggest you use one of the tools mentioned above rather than use this toolbox. Best, Rasmus. DeepLearnToolbox ================ A Matlab toolbox for Deep Learning. Deep Learning is a new subfield of machine learning that focuses on learning deep hierarchical models of data. It is inspired by the human brain's apparent deep (layered, hierarchical) architecture. A good overview of the theory of Deep Learning theory is [Learning Deep Architectures for AI](http://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf) For a more informal introduction, see the following videos by Geoffrey Hinton and Andrew Ng. * [The Next Generation of Neural Networks](http://www.youtube.com/watch?v=AyzOUbkUf3M) (Hinton, 2007) * [Recent Developments in Deep Learning](http://www.youtube.com/watch?v=VdIURAu1-aU) (Hinton, 2010) * [Unsupervised Feature Learning and Deep Learning](http://www.youtube.com/watch?v=ZmNOAtZIgIk) (Ng, 2011) If you use this toolbox in your research please cite [Prediction as a candidate for learning deep hierarchical models of data](http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6284) ``` @MASTERSTHESIS\{IMM2012-06284, author = "R. B. Palm", title = "Prediction as a candidate for learning deep hierarchical models of data", year = "2012", } ``` Contact: rasmusbergpalm at gmail dot com Directories included in the toolbox ----------------------------------- `NN/` - A library for Feedforward Backpropagation Neural Networks `CNN/` - A library for Convolutional Neural Networks `DBN/` - A library for Deep Belief Networks `SAE/` - A library for Stacked Auto-Encoders `CAE/` - A library for Convolutional Auto-Encoders `u

function cae = caeapplygrads（cae）
    cae.sv = 0;
    for j = 1 : numel（cae.a）
        for i = 1 : numel（cae.i）
%             cae.vik{i}{j} = cae.momentum * cae.vik{i}{j} + cae.alpha ./ （cae.sigma + cae.ddik{i}{j}） .* cae.dik{i}{j};
%             cae.vok{i}{j} = cae.momentum * cae.vok{i}{j} + cae.alpha ./ （cae.sigma + cae.ddok{i}{j}） .* cae.dok{i}{j};
            cae.vik{i}{j} = cae.alpha * cae.dik{i}{j};
            cae.vok{i}{j} = cae.alpha * cae.dok{i}{j};
            cae.sv = cae.sv + sum（cae.vik{i}{j}（:） .^ 2）;
            cae.sv = cae.sv + sum（cae.vok{i}{j}（:） .^ 2）;

            cae.ik{i}{j} = cae.ik{i}{j} - cae.vik{i}{j};
            cae.ok{i}{j} = cae.ok{i}{j} - cae.vok{i}{j};
        end
%         cae.vb{j} = cae.momentum * cae.vb{j} + cae.alpha / （cae.sigma + cae.ddb{j}） * cae.db{j};
        cae.vb{j} = cae.alpha * cae.db{j};
        cae.sv = cae.sv + sum（cae.vb{j} .^ 2）;

        cae.b{j} = cae.b{j} - cae.vb{j};
    end

    for i = 1 : numel（cae.o）
%         cae.vc{i} = cae.momentum * cae.vc{i} + cae.alpha / （cae.sigma + cae.ddc{i}） * cae.dc{i};
        cae.vc{i} = cae.alpha * cae.dc{i};
        cae.sv = cae.sv + sum（cae.vc{i} .^ 2）;

        cae.c{i} = cae.c{i} - cae.vc{i};
    end
end

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件        249  2017-08-16 15:48  DeepLearnToolbox-master\.travis.yml

     文件       1219  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caeapplygrads.m

     文件        917  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caebbp.m

     文件       1011  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caebp.m

     文件        259  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caedown.m

     文件        754  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caeexamples.m

     文件       3618  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caenumgradcheck.m

     文件        845  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caesdlm.m

     文件       1148  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caetrain.m

     文件        489  2017-08-16 15:48  DeepLearnToolbox-master\CAE\caeup.m

     文件        173  2017-08-16 15:48  DeepLearnToolbox-master\CAE\max3d.m

     文件       1937  2017-08-16 15:48  DeepLearnToolbox-master\CAE\scaesetup.m

     文件        270  2017-08-16 15:48  DeepLearnToolbox-master\CAE\scaetrain.m

     文件        575  2017-08-16 15:48  DeepLearnToolbox-master\CNN\cnnapplygrads.m

     文件       2141  2017-08-16 15:48  DeepLearnToolbox-master\CNN\cnnbp.m

     文件       1774  2017-08-16 15:48  DeepLearnToolbox-master\CNN\cnnff.m

     文件       3430  2017-08-16 15:48  DeepLearnToolbox-master\CNN\cnnnumgradcheck.m

     文件       2021  2017-08-16 15:48  DeepLearnToolbox-master\CNN\cnnsetup.m

     文件        193  2017-08-16 15:48  DeepLearnToolbox-master\CNN\cnntest.m

     文件        845  2017-08-16 15:48  DeepLearnToolbox-master\CNN\cnntrain.m

     文件   14735220  2017-08-16 15:48  DeepLearnToolbox-master\CNN\mnist_uint8.mat

     文件        981  2017-08-16 16:49  DeepLearnToolbox-master\CNN\test_example_CNN.m

     文件        544  2017-08-16 15:48  DeepLearnToolbox-master\CONTRIBUTING.md

     文件        744  2017-08-16 15:48  DeepLearnToolbox-master\create_readme.sh

     文件        557  2017-08-16 15:48  DeepLearnToolbox-master\DBN\dbnsetup.m

     文件        232  2017-08-16 15:48  DeepLearnToolbox-master\DBN\dbntrain.m

     文件        425  2017-08-16 15:48  DeepLearnToolbox-master\DBN\dbnunfoldtonn.m

     文件         90  2017-08-16 15:48  DeepLearnToolbox-master\DBN\rbmdown.m

     文件       1401  2017-08-16 15:48  DeepLearnToolbox-master\DBN\rbmtrain.m

     文件         89  2017-08-16 15:48  DeepLearnToolbox-master\DBN\rbmup.m

............此处省略56个文件信息