几天前我问了一个问题,但我想这有点太复杂了,我不希望得到任何答案。
我的问题是我需要使用 ANN 进行分类。我读过更好的成本函数(或某些书籍指定的损失函数)是交叉熵,即J(w) = -1/m * sum_i( yi*ln(hw(xi)) + (1-yi)*ln(1 - hw(xi)) )
;i
表示编号。来自训练矩阵的数据X
。我试图在 MATLAB 中应用它,但我发现它真的很难。有几件事我不知道:
- 在给定所有训练数据的情况下,我应该对每个输出求和吗(i = 1,... N,其中 N 是训练的输入数)
- 梯度计算是否正确
- 是正确计算的数值梯度(gradAapprox)。
我有以下 MATLAB 代码。我意识到我可能会要求一些琐碎的事情,但无论如何我希望有人能给我一些如何找到问题的线索。我怀疑问题是计算梯度。
非常感谢。
主脚本:
close all
clear all
L = @(x) (1 + exp(-x)).^(-1);
NN = @(x,theta) theta{2}*[ones(1,size(x,1));L(theta{1}*[ones(size(x,1),1) x]')];
% theta = [10 -30 -30];
x = [0 0; 0 1; 1 0; 1 1];
y = [0.9 0.1 0.1 0.1]';
theta0 = 2*rand(9,1)-1;
options = optimset('gradObj','on','Display','iter');
thetaVec = fminunc(@costFunction,theta0,options,x,y);
theta = cell(2,1);
theta{1} = reshape(thetaVec(1:6),[2 3]);
theta{2} = reshape(thetaVec(7:9),[1 3]);
NN(x,theta)'
成本函数:
function [jVal,gradVal,gradApprox] = costFunction(thetaVec,x,y)
persistent index;
% 1 x x
% 1 x x
% 1 x x
% x = 1 x x
% 1 x x
% 1 x x
% 1 x x
m = size(x,1);
if isempty(index) || index > size(x,1)
index = 1;
end
L = @(x) (1 + exp(-x)).^(-1);
NN = @(x,theta) theta{2}*[ones(1,size(x,1));L(theta{1}*[ones(size(x,1),1) x]')];
theta = cell(2,1);
theta{1} = reshape(thetaVec(1:6),[2 3]);
theta{2} = reshape(thetaVec(7:9),[1 3]);
Dew = cell(2,1);
DewApprox = cell(2,1);
% Forward propagation
a0 = x(index,:)';
z1 = theta{1}*[1;a0];
a1 = L(z1);
z2 = theta{2}*[1;a1];
a2 = L(z2);
% Back propagation
d2 = 1/m*(a2 - y(index))*L(z2)*(1-L(z2));
Dew{2} = [1;a1]*d2;
d1 = [1;a1].*(1 - [1;a1]).*theta{2}'*d2;
Dew{1} = [1;a0]*d1(2:end)';
% NNRes = NN(x,theta)';
% jVal = -1/m*sum(NNRes-y)*NNRes*(1-NNRes);
jVal = -1/m*(a2 - y(index))*a2*(1-a2);
gradVal = [Dew{1}(:);Dew{2}(:)];
gradApprox = CalcGradApprox(0.0001);
index = index + 1;
function output = CalcGradApprox(epsilon)
output = zeros(size(gradVal));
for n=1:length(thetaVec)
thetaVecMin = thetaVec;
thetaVecMax = thetaVec;
thetaVecMin(n) = thetaVec(n) - epsilon;
thetaVecMax(n) = thetaVec(n) + epsilon;
thetaMin = cell(2,1);
thetaMax = cell(2,1);
thetaMin{1} = reshape(thetaVecMin(1:6),[2 3]);
thetaMin{2} = reshape(thetaVecMin(7:9),[1 3]);
thetaMax{1} = reshape(thetaVecMax(1:6),[2 3]);
thetaMax{2} = reshape(thetaVecMax(7:9),[1 3]);
a2min = NN(x(index,:),thetaMin)';
a2max = NN(x(index,:),thetaMax)';
jValMin = -1/m*(a2min-y(index))*a2min*(1-a2min);
jValMax = -1/m*(a2max-y(index))*a2max*(1-a2max);
output(n) = (jValMax - jValMin)/2/epsilon;
end
end
end
编辑:下面我为那些可能感兴趣的人展示我的 costFunction 的正确版本。
function [jVal,gradVal,gradApprox] = costFunction(thetaVec,x,y)
m = size(x,1);
L = @(x) (1 + exp(-x)).^(-1);
NN = @(x,theta) L(theta{2}*[ones(1,size(x,1));L(theta{1}*[ones(size(x,1),1) x]')]);
theta = cell(2,1);
theta{1} = reshape(thetaVec(1:6),[2 3]);
theta{2} = reshape(thetaVec(7:9),[1 3]);
Delta = cell(2,1);
Delta{1} = zeros(size(theta{1}));
Delta{2} = zeros(size(theta{2}));
D = cell(2,1);
D{1} = zeros(size(theta{1}));
D{2} = zeros(size(theta{2}));
jVal = 0;
for in = 1:size(x,1)
% Forward propagation
a1 = [1;x(in,:)']; % added bias to a0
z2 = theta{1}*a1;
a2 = [1;L(z2)]; % added bias to a1
z3 = theta{2}*a2;
a3 = L(z3);
% Back propagation
d3 = a3 - y(in);
d2 = theta{2}'*d3.*a2.*(1 - a2);
Delta{2} = Delta{2} + d3*a2';
Delta{1} = Delta{1} + d2(2:end)*a1';
jVal = jVal + sum( y(in)*log(a3) + (1-y(in))*log(1-a3) );
end
D{1} = 1/m*Delta{1};
D{2} = 1/m*Delta{2};
jVal = -1/m*jVal;
gradVal = [D{1}(:);D{2}(:)];
gradApprox = CalcGradApprox(x(in,:),0.0001);
% Nested function to calculate gradApprox
function output = CalcGradApprox(x,epsilon)
output = zeros(size(thetaVec));
for n=1:length(thetaVec)
thetaVecMin = thetaVec;
thetaVecMax = thetaVec;
thetaVecMin(n) = thetaVec(n) - epsilon;
thetaVecMax(n) = thetaVec(n) + epsilon;
thetaMin = cell(2,1);
thetaMax = cell(2,1);
thetaMin{1} = reshape(thetaVecMin(1:6),[2 3]);
thetaMin{2} = reshape(thetaVecMin(7:9),[1 3]);
thetaMax{1} = reshape(thetaVecMax(1:6),[2 3]);
thetaMax{2} = reshape(thetaVecMax(7:9),[1 3]);
a3min = NN(x,thetaMin)';
a3max = NN(x,thetaMax)';
jValMin = 0;
jValMax = 0;
for inn=1:size(x,1)
jValMin = jValMin + sum( y(inn)*log(a3min) + (1-y(inn))*log(1-a3min) );
jValMax = jValMax + sum( y(inn)*log(a3max) + (1-y(inn))*log(1-a3max) );
end
jValMin = 1/m*jValMin;
jValMax = 1/m*jValMax;
output(n) = (jValMax - jValMin)/2/epsilon;
end
end
end