# machine-learning第五周 上机作业

1、导数（变化率）与微分 （变化量）

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;

% ====================== 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
%         the cost function with respect to Theta1 and Theta2 in Theta1_grad and
%         Theta2_grad, respectively. After implementing Part 2, you can check
%
%         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
%               and Theta2_grad from Part 2.
%

% part 1

% Theta1 has size 25 x 401
% Theta2 has size 10 x 26

y = eye(num_labels)(y,:); %5000x10

a1 = [ones(m, 1) X];      %5000x401

z2 = a1 * Theta1' ;
a2 = sigmoid(z2);
n = size(a2,1);
a2 = [ones(n, 1) a2] ;    %5000x26

a3 = sigmoid(a2 * Theta2'); %5000x10

J = sum( sum( -y.* log(a3) -  (1-y).*log(1-a3) ))/ m;

% pay attention :" Theta1(:,2:end) " , no "Theta1" .
regularized = lambda/(2*m) * (sum(sum(Theta1(:,2:end).^2)) + sum(sum(Theta2(:,2:end).^2)) );

J = J + regularized;

% part 2

delta3 = a3-y;            %5000x10

delta2 = delta3 * Theta2 ;
delta2 = delta2(:,2:end);

delta2 = delta2 .* sigmoidGradient(z2);  %5000x25

Delta_1 = zeros(size(Theta1));
Delta_2 = zeros(size(Theta2));

Delta_1 = Delta_1 + delta2' * a1 ;

Delta_2 = Delta_2 + delta3' * a2 ;

regularized_1 = lambda/m * Theta1;
regularized_2 = lambda/m * Theta2;

regularized_1(:,1) = zeros(size(regularized_1,1),1);
regularized_2(:,1) = zeros(size(regularized_2,1),1);

%Theta1_grad = ((1/m) * Delta_1) + ((lambda/m) * (Theta1));
%Theta2_grad = ((1/m) * Delta_2) + ((lambda/m) * (Theta2));

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

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

end

08-28 129
12-15 1万+
03-16 756
04-17 9077
04-10 6万+
07-30 2142
10-17 4747