==========================================================================================
最近一直在看Deep Learning，各类博客、论文看得不少
但是说实话，这样做有些疏于实现，一来呢自己的电脑也不是很好，二来呢我目前也没能力自己去写一个toolbox
只是跟着Andrew Ng的UFLDL tutorial 写了些已有框架的代码(这部分的代码见github)
后来发现了一个matlab的Deep Learning的toolbox，发现其代码很简单，感觉比较适合用来学习算法
再一个就是matlab的实现可以省略掉很多数据结构的代码，使算法思路非常清晰
所以我想在解读这个toolbox的代码的同时来巩固自己学到的，同时也为下一步的实践打好基础
(本文只是从代码的角度解读算法，具体的算法理论步骤还是需要去看paper的
我会在文中给出一些相关的paper的名字，本文旨在梳理一下算法过程，不会深究算法原理和公式)
==========================================================================================
使用的代码：DeepLearnToolbox ，下载地址：点击打开，感谢该toolbox的作者
==========================================================================================
第一章从分析NN(neural network)开始，因为这是整个deep learning的大框架，参见UFLDL
==========================================================================================
首先看一下\tests\test_example_NN.m ，跳过对数据进行normalize的部分，最关键的就是：
（为了注释显示有颜色，我把matlab代码中的%都改成了//）
nn = nnsetup([784 100 10]);
opts.numepochs = 1; // Number of full sweeps through data
opts.batchsize = 100; // Take a mean gradient step over this many samples
[nn, L] = nntrain(nn, train_x, train_y, opts);
[er, bad] = nntest(nn, test_x, test_y);很简单的几步就训练了一个NN，我们发现其中最重要的几个函数就是nnsetup,nntrain和nntest了
那么我们分别来分析着几个函数，\NN\nnsetup.m
nnsetup
function nn = nnsetup(architecture)
//首先从传入的architecture中获得这个网络的整体结构，nn.n表示这个网络有多少层，可以参照上面的样例调用nnsetup([784 100 10])加以理解
nn.size = architecture;
nn.n = numel(nn.size);
//接下来是一大堆的参数，这个我们到具体用的时候再加以说明
nn.activation_function = 'tanh_opt'; // Activation functions of hidden layers: 'sigm' (sigmoid) or 'tanh_opt' (optimal tanh).
nn.learningRate = 2; // learning rate Note: typically needs to be lower when using 'sigm' activation function and non-normalized inputs.
nn.momentum = 0.5; // Momentum
nn.scaling_learningRate = 1; // Scaling factor for the learning rate (each epoch)
nn.weightPenaltyL2 = 0; // L2 regularization
nn.nonSparsityPenalty = 0; // Non sparsity penalty
nn.sparsityTarget = 0.05; // Sparsity target
nn.inputZeroMaskedFraction = 0; // Used for Denoising AutoEncoders
nn.dropoutFraction = 0; // Dropout level (http://www.cs.toronto.edu/~hinton/absps/dropout.pdf)
nn.testing = 0; // Internal variable. nntest sets this to one.
nn.output = 'sigm'; // output unit 'sigm' (=logistic), 'softmax' and 'linear'
//对每一层的网络结构进行初始化，一共三个参数W,vW，p，其中W是主要的参数
//vW是更新参数时的临时参数，p是所谓的sparsity，(等看到代码了再细讲)
for i = 2 : nn.n
// weights and weight momentum
nn.W{i - 1} = (rand(nn.size(i), nn.size(i - 1)+1) - 0.5) * 2 * 4 * sqrt(6 / (nn.size(i) + nn.size(i - 1)));
nn.vW{i - 1} = zeros(size(nn.W{i - 1}));
// average activations (for use with sparsity)
nn.p{i} = zeros(1, nn.size(i));
end
end
nntrain
setup大概就这样一个过程，下面就到了train了，打开\NN\nntrain.m
我们跳过那些检验传入数据是否正确的代码，直接到关键的部分
denoising 的部分请参考论文：Extracting and Composing Robust Features with Denoising Autoencoders
m = size(train_x, 1);
//m是训练样本的数量
//注意在调用的时候我们设置了opt，batchsize是做batch gradient时候的大小
batchsize = opts.batchsize; numepochs = opts.numepochs;
numbatches = m / batchsize; //计算batch的数量
assert(rem(numbatches, 1) == 0, 'numbatches must be a integer');
L = zeros(numepochs*numbatches,1);
n = 1;
//numepochs是循环的次数
for i = 1 : numepochs
tic;
kk = randperm(m);
//把batches打乱顺序进行训练，randperm(m)生成一个乱序的1到m的数组
for l = 1 : numbatches
batch_x = train_x(kk((l - 1) * batchsize + 1 : l * batchsize), :);
//Add noise to input (for use in denoising autoencoder)
//加入noise，这是denoising autoencoder需要使用到的部分
//这部分请参见《Extracting and Composing Robust Features with Denoising Autoencoders》这篇论文
//具体加入的方法就是把训练样例中的一些数据调整变为0，inputZeroMaskedFraction表示了调整的比例
if(nn.inputZeroMaskedFraction ~= 0)
batch_x = batch_x.*(rand(size(batch_x))>nn.inputZeroMaskedFraction);
end
batch_y = train_y(kk((l - 1) * batchsize + 1 : l * batchsize), :);
//这三个函数
//nnff是进行前向传播，nnbp是后向传播，nnapplygrads是进行梯度下降
//我们在下面分析这些函数的代码
nn = nnff(nn, batch_x, batch_y);
nn = nnbp(nn);
nn = nnapplygrads(nn);
L(n) = nn.L;
n = n + 1;
end
t = toc;
if ishandle(fhandle)
if opts.validation == 1
loss = nneval(nn, loss, train_x, train_y, val_x, val_y);
else
loss = nneval(nn, loss, train_x, train_y);
end
nnupdatefigures(nn, fhandle, loss, opts, i);
end
disp(['epoch ' num2str(i) '/' num2str(opts.numepochs) '. Took ' num2str(t) ' seconds' '. Mean squared error on training set is ' num2str(mean(L((n-numbatches):(n-1))))]);
nn.learningRate = nn.learningRate * nn.scaling_learningRate;
end下面分析三个函数nnff,nnbp和nnapplygrads
nnff
nnff就是进行feedforward pass，其实非常简单，就是整个网络正向跑一次就可以了
当然其中有dropout和sparsity的计算
具体的参见论文“Improving Neural Networks with Dropout“和Autoencoders and Sparsity
function nn = nnff(nn, x, y)
//NNFF performs a feedforward pass
// nn = nnff(nn, x, y) returns an neural network structure with updated
// layer activations, error and loss (nn.a, nn.e and nn.L)
n = nn.n;
m = size(x, 1);
x = [ones(m,1) x];
nn.a{1} = x;
//feedforward pass
for i = 2 : n-1
//根据选择的激活函数不同进行正向传播计算
//你可以回过头去看nnsetup里面的第一个参数activation_function
//sigm就是sigmoid函数,tanh_opt就是tanh的函数，这个toolbox好像有一点改变
//tanh_opt是1.7159*tanh(2/3.*A)
switch nn.activation_function
case 'sigm'
// Calculate the unit's outputs (including the bias term)
nn.a{i} = sigm(nn.a{i - 1} * nn.W{i - 1}');
case 'tanh_opt'
nn.a{i} = tanh_opt(nn.a{i - 1} * nn.W{i - 1}');
end
//dropout的计算部分部分 dropoutFraction 是nnsetup中可以设置的一个参数
if(nn.dropoutFraction > 0)
if(nn.testing)
nn.a{i} = nn.a{i}.*(1 - nn.dropoutFraction);
else
nn.dropOutMask{i} = (rand(size(nn.a{i}))>nn.dropoutFraction);
nn.a{i} = nn.a{i}.*nn.dropOutMask{i};
end
end
//计算sparsity，nonSparsityPenalty 是对没达到sparsitytarget的参数的惩罚系数
//calculate running exponential activations for use with sparsity
if(nn.nonSparsityPenalty>0)
nn.p{i} = 0.99 * nn.p{i} + 0.01 * mean(nn.a{i}, 1);
end
//Add the bias term
nn.a{i} = [ones(m,1) nn.a{i}];
end
switch nn.output
case 'sigm'
nn.a{n} = sigm(nn.a{n - 1} * nn.W{n - 1}');
case 'linear'
nn.a{n} = nn.a{n - 1} * nn.W{n - 1}';
case 'softmax'
nn.a{n} = nn.a{n - 1} * nn.W{n - 1}';
nn.a{n} = exp(bsxfun(@minus, nn.a{n}, max(nn.a{n},[],2)));
nn.a{n} = bsxfun(@rdivide, nn.a{n}, sum(nn.a{n}, 2));
end
//error and loss
//计算error
nn.e = y - nn.a{n};
switch nn.output
case {'sigm', 'linear'}
nn.L = 1/2 * sum(sum(nn.e .^ 2)) / m;
case 'softmax'
nn.L = -sum(sum(y .* log(nn.a{n}))) / m;
end
end
nnbp
代码：\NN\nnbp.m
nnbp呢是进行back propagation的过程，过程还是比较中规中矩，和ufldl中的Neural Network讲的基本一致
值得注意的还是dropout和sparsity的部分
if(nn.nonSparsityPenalty>0)
pi = repmat(nn.p{i}, size(nn.a{i}, 1), 1);
sparsityError = [zeros(size(nn.a{i},1),1) nn.nonSparsityPenalty * (-nn.sparsityTarget ./ pi + (1 - nn.sparsityTarget) ./ (1 - pi))];
end
// Backpropagate first derivatives
if i+1==n % in this case in d{n} there is not the bias term to be removed
d{i} = (d{i + 1} * nn.W{i} + sparsityError) .* d_act; // Bishop (5.56)
else // in this case in d{i} the bias term has to be removed
d{i} = (d{i + 1}(:,2:end) * nn.W{i} + sparsityError) .* d_act;
end
if(nn.dropoutFraction>0)
d{i} = d{i} .* [ones(size(d{i},1),1) nn.dropOutMask{i}];
enddW{i}基本就是计算的gradient了，只是后面还要加入一些东西，进行一些修改
具体原理参见论文“Improving Neural Networks with Dropout“ 以及 Autoencoders and Sparsity的内容
nnapplygrads
代码文件：\NN\nnapplygrads.m
for i = 1 : (nn.n - 1)
if(nn.weightPenaltyL2>0)
dW = nn.dW{i} + nn.weightPenaltyL2 * nn.W{i};
else
dW = nn.dW{i};
end
dW = nn.learningRate * dW;
if(nn.momentum>0)
nn.vW{i} = nn.momentum*nn.vW{i} + dW;
dW = nn.vW{i};
end
nn.W{i} = nn.W{i} - dW;
end这个内容就简单了，nn.weightPenaltyL2 是weight decay的部分，也是nnsetup时可以设置的一个参数
有的话就加入weight Penalty，防止过拟合，然后再根据momentum的大小调整一下，最后改变nn.W{i}即可
nntest
nntest再简单不过了，就是调用一下nnpredict，在和test的集合进行比较
function [er, bad] = nntest(nn, x, y)
labels = nnpredict(nn, x);
[~, expected] = max(y,[],2);
bad = find(labels ~= expected);
er = numel(bad) / size(x, 1);
end
nnpredict
代码文件：\NN\nnpredict.m
function labels = nnpredict(nn, x)
nn.testing = 1;
nn = nnff(nn, x, zeros(size(x,1), nn.size(end)));
nn.testing = 0;
[~, i] = max(nn.a{end},[],2);
labels = i;
end
继续非常简单，predict不过是nnff一次，得到最后的output~~
max(nn.a{end},[],2); 是返回每一行的最大值以及所在的列数，所以labels返回的就是标号啦
(这个test好像是专门用来test 分类问题的，我们知道nnff得到最后的值即可)