Pertanyaan

Mohon maafkan saya menanyakan pertanyaan khusus kursus Coursera ML. Semoga seseorang yang melakukan couser dapat menjawab.

Dalam Coursera ML Minggu 4 Klasifikasi Multikelas dan Jaringan Neural tugas, mengapa gradien bobot (theta) menambah (menambah) turunannya, bukan mengurangi?

% Calculate the gradients of Weight2
% Derivative at Loss function J=L(Z) : dJ/dZ = (oi-yi)/oi(1-oi)
% Derivative at Sigmoid activation function dZ/dY = oi(1-oi)

delta_theta2 = oi - yi;  % <--- (dJ/dZ) * (dZ/dY) 

# Using +/plus NOT -/minus
Theta2_grad = Theta2_grad +     <-------- Why plus(+)?
              bsxfun(@times, hi, transpose(delta_theta2)); 

Kutipan Kode

for i = 1:m  
    % i is training set index of X (including bias). X(i, :) is 401 data.
    xi = X(i, :);
    yi = Y(i, :);
    
    % hi is the i th output of the hidden layer. H(i, :) is 26 data.
    hi = H(i, :);
    
    % oi is the i th output layer. O(i, :) is 10 data.
    oi = O(i, :);
    
    %------------------------------------------------------------------------
    % Calculate the gradients of Theta2
    %------------------------------------------------------------------------
    delta_theta2 = oi - yi;
    Theta2_grad = Theta2_grad + bsxfun(@times, hi, transpose(delta_theta2));
 
    %------------------------------------------------------------------------
    % Calculate the gradients of Theta1
    %------------------------------------------------------------------------
    % Derivative of g(z): g'(z)=g(z)(1-g(z)) where g(z) is sigmoid(H_NET).
    dgz = (hi .* (1 - hi));
    delta_theta1 = dgz .* sum(bsxfun(@times, Theta2, transpose(delta_theta2)));
    % There is no input into H0, hence there is no theta for H0. Remove H0.
    delta_theta1 = delta_theta1(2:end);
    Theta1_grad = Theta1_grad + bsxfun(@times, xi, transpose(delta_theta1));
end

Saya pikir itu mengurangi turunannya.

• Turunan dari Binary Cross Entropy - mengapa tanda-tanda saya tidak benar?