In [1]:
clear ; close all; clc
In [2]:
%% Initialization
%% Setup the parameters you will use for this exercise
input_layer_size = 400; % 20x20 Input Images of Digits
hidden_layer_size = 25; % 25 hidden units
num_labels = 10; % 10 labels, from 1 to 10
% (note that we have mapped "0" to label 10)
In [3]:
% Load Training Data
fprintf('Loading and Visualizing Data ...\n')
load('./data/ex4data1.mat');
m = size(X, 1);
% Randomly select 100 data points to display
sel = randperm(size(X, 1));
sel = sel(1:100);
displayData(X(sel, :));
In [4]:
% Load pre-initialized weights for neural network
fprintf('\nLoading Saved Neural Network Parameters ...\n')
% Load the weights into variables Theta1 and Theta2
load('./data/ex4weights.mat');
% Unroll parameters
nn_params = [Theta1(:) ; Theta2(:)];
In [9]:
% Compute Cost
fprintf('\nFeedforward Using Neural Network ...\n')
% Weight regularization parameter (we set this to 0 here).
lambda = 0;
J = nnCostFunction(nn_params, input_layer_size, hidden_layer_size, num_labels, X, y, lambda);
fprintf(['Cost at parameters (loaded from ex4weights): %f'], J);
In [11]:
% Implement Regularization
printf('\nChecking Cost Function (w/ Regularization) ... \n')
% Weight regularization parameter (we set this to 1 here).
lambda = 1;
J = nnCostFunction(nn_params, input_layer_size, hidden_layer_size, ...
num_labels, X, y, lambda);
fprintf(['Cost at parameters (loaded from ex4weights): %f '], J);
In [12]:
fprintf('\nEvaluating sigmoid gradient...\n')
g = sigmoidGradient([-1 -0.5 0 0.5 1]);
fprintf('Sigmoid gradient evaluated at [-1 -0.5 0 0.5 1]:\n ');
fprintf('%f ', g);
fprintf('\n\n');
In [13]:
fprintf('\nInitializing Neural Network Parameters ...\n')
initial_Theta1 = randInitializeWeights(input_layer_size, hidden_layer_size);
initial_Theta2 = randInitializeWeights(hidden_layer_size, num_labels);
% Unroll parameters
initial_nn_params = [initial_Theta1(:) ; initial_Theta2(:)];
In [14]:
fprintf('\nChecking Backpropagation... \n');
% Check gradients by running checkNNGradients
checkNNGradients;
In [15]:
fprintf('\nChecking Backpropagation (w/ Regularization) ... \n')
% Check gradients by running checkNNGradients
lambda = 3;
checkNNGradients(lambda);
% Also output the costFunction debugging values
debug_J = nnCostFunction(nn_params, input_layer_size, ...
hidden_layer_size, num_labels, X, y, lambda);
fprintf(['\n\nCost at (fixed) debugging parameters (w/ lambda = %f): %f ' ...
'\n(for lambda = 3, this value should be about 0.576051)\n\n'], lambda, debug_J);
In [16]:
fprintf('\nTraining Neural Network... \n')
% After you have completed the assignment, change the MaxIter to a larger
% value to see how more training helps.
options = optimset('MaxIter', 50);
% You should also try different values of lambda
lambda = 1;
% Create "short hand" for the cost function to be minimized
costFunction = @(p) nnCostFunction(p, ...
input_layer_size, ...
hidden_layer_size, ...
num_labels, X, y, lambda);
% Now, costFunction is a function that takes in only one argument (the
% neural network parameters)
[nn_params, cost] = fmincg(costFunction, initial_nn_params, options);
% Obtain Theta1 and Theta2 back from nn_params
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));
In [17]:
fprintf('\nVisualizing Neural Network... \n')
displayData(Theta1(:, 2:end));
In [18]:
pred = predict(Theta1, Theta2, X);
fprintf('\nTraining Set Accuracy: %f\n', mean(double(pred == y)) * 100);
In [ ]: