Question

此代码是Andrew Ng的机器学习课程的编程作业。

该函数期望行向量[J grad]。代码计算J（尽管错误，但这不是问题），我为grad添加了一个虚拟值（因为我还没有编写代码来计算它）。当我运行代码时，它只输出ans作为标量，其值为J。 grad去了哪里？

function [J grad] = nnCostFunction(nn_params, ...
                               input_layer_size, ...
                               hidden_layer_size, ...
                               num_labels, ...
                               X, y, lambda)
%NNCOSTFUNCTION Implements the neural network cost function for a two layer
%neural network which performs classification
%   [J grad] = NNCOSTFUNCTON(nn_params, hidden_layer_size, num_labels, ...
%   X, y, lambda) computes the cost and gradient of the neural network. The
%   parameters for the neural network are "unrolled" into the vector
%   nn_params and need to be converted back into the weight matrices. 
% 
%   The returned parameter grad should be a "unrolled" vector of the
%   partial derivatives of the neural network.
%

% Reshape nn_params back into the parameters Theta1 and Theta2, the weight matrices
% for our 2 layer neural network
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));

% Setup some useful variables
m = size(X, 1);

% You need to return the following variables correctly 
J = 0;
Theta1_grad = zeros(size(Theta1));
Theta2_grad = zeros(size(Theta2));

% ====================== YOUR CODE HERE ======================
% Instructions: You should complete the code by working through the
%               following parts.
%
% Part 1: Feedforward the neural network and return the cost in the
%         variable J. After implementing Part 1, you can verify that your
%         cost function computation is correct by verifying the cost
%         computed in ex4.m
%
% Part 2: Implement the backpropagation algorithm to compute the gradients
%         Theta1_grad and Theta2_grad. You should return the partial derivatives of
%         the cost function with respect to Theta1 and Theta2 in Theta1_grad and
%         Theta2_grad, respectively. After implementing Part 2, you can check
%         that your implementation is correct by running checkNNGradients
%
%         Note: The vector y passed into the function is a vector of labels
%               containing values from 1..K. You need to map this vector into a 
%               binary vector of 1's and 0's to be used with the neural network
%               cost function.
%
%         Hint: We recommend implementing backpropagation using a for-loop
%               over the training examples if you are implementing it for the 
%               first time.
%
% Part 3: Implement regularization with the cost function and gradients.
%
%         Hint: You can implement this around the code for
%               backpropagation. That is, you can compute the gradients for
%               the regularization separately and then add them to Theta1_grad
%               and Theta2_grad from Part 2.
%

% PART 1

a1 = [ones(m,1) X]; % set a1 to equal X and add column of 1's

z2 = a1 * Theta1'; % matrix times matrix [5000*401 * 401*25 = 5000*25]
a2 = [ones(m,1),sigmoid(z2)]; % sigmoid function on matrix [5000*26]
z3 = a2 * Theta2'; % matrix times matrix [5000*26 * 26*10 = 5000 * 10]
hox = sigmoid(z3); % sigmoid function on matrix [5000*10]

for k = 1:num_labels

    yk = y == k; % using the correct column vector y each loop
    J = J + sum(-yk.*log(hox(:,k)) - (1-yk).*log(1-hox(:,k)));

end

J = 1/m * J;   

% -------------------------------------------------------------

% =========================================================================

% Unroll gradients
% grad = [Theta1_grad(:) ; Theta2_grad(:)];
grad = 6.6735;

end

Answer 1

您已在函数声明中指定该函数可以同时返回多个输出值：

function [J grad] = nnCostFunction(nn_params, ...   % etc

如果您通过分配变量矩阵而不是单个变量来“请求”它们，则可以捕获两个输出：

[a, b] = nnCostFunction(input1, input2, etc)

如果你不这样做，你实际上只是“请求”第一个返回的变量：

a = nnCostFunction(input1, input2, etc)  % output 'b' is discarded.

如果您没有指定要分配的变量，默认情况下，八度音程会分配给“默认”变量ans。所以它基本上等同于做

ans = nnCostFunction(input1, input2, etc)  % output 'b' is discarded.

请参阅find函数的文档（例如，在八度音阶终端中键入help find）以查看此类函数的示例。

PS。如果您只想要第二个输出并且不想“浪费”第一个的变量名称，则可以通过将~指定为第一个输出来执行此操作，例如：

[~, b] = nnCostFunction(input1, input2, etc)  % output 'a' is discarded

Octave：函数没有返回预期值？

1 个答案: