Machine learning 用神经网络实现连续回归中的梯度
我正在尝试实现一个回归NN,它有3层(1个输入层、1个隐藏层和1个输出层,结果是连续的)。作为基础,我从类中提取了分类NN,但更改了成本函数和梯度计算,以适应回归问题(而不是分类问题): 我现在的功能是:Machine learning 用神经网络实现连续回归中的梯度,machine-learning,neural-network,gradient,regression,Machine Learning,Neural Network,Gradient,Regression,我正在尝试实现一个回归NN,它有3层(1个输入层、1个隐藏层和1个输出层,结果是连续的)。作为基础,我从类中提取了分类NN,但更改了成本函数和梯度计算,以适应回归问题(而不是分类问题): 我现在的功能是: function [J grad] = nnCostFunctionLinear(nn_params, ... input_layer_size, ...
function [J grad] = nnCostFunctionLinear(nn_params, ...
input_layer_size, ...
hidden_layer_size, ...
num_labels, ...
X, y, lambda)
Theta1 = reshape(nn_params(1:hidden_layer_size * (input_layer_size + 1)), ...
hidden_layer_size, (input_layer_size + 1));
Theta2 = reshape(nn_params((1 + (hidden_layer_size * (input_layer_size + 1))):end), ...
num_labels, (hidden_layer_size + 1));
m = size(X, 1);
a1 = X;
a1 = [ones(m, 1) a1];
a2 = a1 * Theta1';
a2 = [ones(m, 1) a2];
a3 = a2 * Theta2';
Y = y;
J = 1/(2*m)*sum(sum((a3 - Y).^2))
th1 = Theta1;
th1(:,1) = 0; %set bias = 0 in reg. formula
th2 = Theta2;
th2(:,1) = 0;
t1 = th1.^2;
t2 = th2.^2;
th = sum(sum(t1)) + sum(sum(t2));
th = lambda * th / (2*m);
J = J + th; %regularization
del_3 = a3 - Y;
t1 = del_3'*a2;
Theta2_grad = 2*(t1)/m + lambda*th2/m;
t1 = del_3 * Theta2;
del_2 = t1 .* a2;
del_2 = del_2(:,2:end);
t1 = del_2'*a1;
Theta1_grad = 2*(t1)/m + lambda*th1/m;
grad = [Theta1_grad(:) ; Theta2_grad(:)];
end
然后我在fmincg算法中使用这个函数,但在第一次迭代中,fmincg结束了它的工作。我认为我的梯度是错误的,但我找不到错误
有人能帮忙吗?如果我理解正确,您的第一块代码(如下所示)—— 是在输出层获得输出a(3) Ng关于NN的幻灯片具有以下配置,用于计算a(3)。它与您的代码呈现的内容不同
- 在中间/输出层,您没有执行激活功能
,例如g
功能sigmoid
J
,Ng的幻灯片具有以下公式:
我不明白为什么您可以使用以下公式计算:
J = 1/(2*m)*sum(sum((a3 - Y).^2))
因为您根本不包括
log
函数 Mikhaill,我也一直在使用神经网络进行连续回归,在某些时候也遇到了类似的问题。在这里最好的做法是在运行模型之前,根据数值计算测试梯度计算。如果这不正确,fmincg将无法训练模型。(顺便说一句,我不鼓励你使用数值梯度,因为所涉及的时间要大得多)
考虑到您从Ng的Coursera课程中获得了这个想法,我将为您实现一个可能的解决方案,尝试使用相同的八度符号
% Cost function without regularization.
J = 1/2/m^2*sum((a3-Y).^2);
% In case it´s needed, regularization term is added (i.e. for Training).
if (reg==true);
J=J+lambda/2/m*(sum(sum(Theta1(:,2:end).^2))+sum(sum(Theta2(:,2:end).^2)));
endif;
% Derivatives are computed for layer 2 and 3.
d3=(a3.-Y);
d2=d3*Theta2(:,2:end);
% Theta grad is computed without regularization.
Theta1_grad=(d2'*a1)./m;
Theta2_grad=(d3'*a2)./m;
% Regularization is added to grad computation.
Theta1_grad(:,2:end)=Theta1_grad(:,2:end)+(lambda/m).*Theta1(:,2:end);
Theta2_grad(:,2:end)=Theta2_grad(:,2:end)+(lambda/m).*Theta2(:,2:end);
% Unroll gradients.
grad = [Theta1_grad(:) ; Theta2_grad(:)];
请注意,由于您已经去掉了所有的sigmoid激活,因此导数计算非常简单,并简化了原始代码
下一步:
1.检查此代码以了解它对您的问题是否有意义。
2.使用渐变检查测试渐变计算。
3.最后,使用fmincg并检查是否得到不同的结果。尝试使用sigmoid函数来计算第二层(隐藏层)值,并在计算目标(输出)值时避免使用sigmoid
在将输入传递给NNCOST函数之前,对输入进行规范化。根据第5周的《线性系统NN课堂讲稿指南》,您应在初始代码中进行以下更改:
log()和sigmoid()-逻辑回归NN的方法。在coursera的例子中,这是癌症检测,但我想预测房屋成本Hi Mikhail,这是一个一年多前的问题,但我想知道你是否已经解决了这个问题?实际上,另一个人问了同样的问题,我在那里提供了我的代码,与Andrew Ng的checkNNGradients(lambda)相比,得到了1e-4的相对差异:如果你已经解决了这个问题,得到的相对差异更小,请通过回答你自己的问题来更新;否则,希望我的代码有帮助。谢谢那是什么语言??这不是octave/matlab(吴教授在..中教授的内容)@javadba,这是octave
% Cost function without regularization.
J = 1/2/m^2*sum((a3-Y).^2);
% In case it´s needed, regularization term is added (i.e. for Training).
if (reg==true);
J=J+lambda/2/m*(sum(sum(Theta1(:,2:end).^2))+sum(sum(Theta2(:,2:end).^2)));
endif;
% Derivatives are computed for layer 2 and 3.
d3=(a3.-Y);
d2=d3*Theta2(:,2:end);
% Theta grad is computed without regularization.
Theta1_grad=(d2'*a1)./m;
Theta2_grad=(d3'*a2)./m;
% Regularization is added to grad computation.
Theta1_grad(:,2:end)=Theta1_grad(:,2:end)+(lambda/m).*Theta1(:,2:end);
Theta2_grad(:,2:end)=Theta2_grad(:,2:end)+(lambda/m).*Theta2(:,2:end);
% Unroll gradients.
grad = [Theta1_grad(:) ; Theta2_grad(:)];
function [J grad] = nnCostFunction1(nnParams, ...
inputLayerSize, ...
hiddenLayerSize, ...
numLabels, ...
X, y, lambda)
Theta1 = reshape(nnParams(1:hiddenLayerSize * (inputLayerSize + 1)), ...
hiddenLayerSize, (inputLayerSize + 1));
Theta2 = reshape(nnParams((1 + (hiddenLayerSize * (inputLayerSize + 1))):end), ...
numLabels, (hiddenLayerSize + 1));
Theta1Grad = zeros(size(Theta1));
Theta2Grad = zeros(size(Theta2));
m = size(X,1);
a1 = [ones(m, 1) X]';
z2 = Theta1 * a1;
a2 = sigmoid(z2);
a2 = [ones(1, m); a2];
z3 = Theta2 * a2;
a3 = z3;
Y = y';
r1 = lambda / (2 * m) * sum(sum(Theta1(:, 2:end) .* Theta1(:, 2:end)));
r2 = lambda / (2 * m) * sum(sum(Theta2(:, 2:end) .* Theta2(:, 2:end)));
J = 1 / ( 2 * m ) * (a3 - Y) * (a3 - Y)' + r1 + r2;
delta3 = a3 - Y;
delta2 = (Theta2' * delta3) .* sigmoidGradient([ones(1, m); z2]);
delta2 = delta2(2:end, :);
Theta2Grad = 1 / m * (delta3 * a2');
Theta2Grad(:, 2:end) = Theta2Grad(:, 2:end) + lambda / m * Theta2(:, 2:end);
Theta1Grad = 1 / m * (delta2 * a1');
Theta1Grad(:, 2:end) = Theta1Grad(:, 2:end) + lambda / m * Theta1(:, 2:end);
grad = [Theta1Grad(:) ; Theta2Grad(:)];
end