Created
December 11, 2012 14:35
-
-
Save blandinw/4258990 to your computer and use it in GitHub Desktop.
Coursera: Neural Net Learning
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
% https://class.coursera.org/ml-2012-002 | |
for i = 1:m | |
% actual class for this example | |
actual = zeros(1, num_labels); | |
actual(y(i)) = 1; | |
% compute activation vectors for the 3 layers | |
a1 = X(i,:); | |
z2 = [1 a1] * Theta1'; | |
a2 = sigmoid(z2); | |
z3 = [1 a2] * Theta2'; | |
a3 = sigmoid(z3); | |
% Part 1 - cost | |
% compute cost for this example | |
costs = actual.*log(a3) + (1-actual).*log(1-a3); | |
J += sum(costs); | |
% Part 2 - backprop | |
d3 = (a3 - actual)'; | |
d2 = ((Theta2'(2:end,:) * d3) .* sigmoidGradient(z2)'); | |
Theta2_grad += d3 * [1 a2]; | |
Theta1_grad += d2 * [1 a1]; | |
end | |
% add regularization term (sum over every node, skip bias units) | |
regularization = lambda/(2*m) * sum([Theta1(:,2:end)(:) ; Theta2(:,2:end)(:)] .^ 2); | |
J = (-1/m * J) + regularization; | |
% compute Deltas | |
Theta2_grad = 1/m * Theta2_grad; | |
Theta2_grad(:,2:end) += (lambda/m)*Theta2(:,2:end); | |
Theta1_grad = 1/m * Theta1_grad; | |
Theta1_grad(:,2:end) += (lambda/m)*Theta1(:,2:end); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment