machine-learning-ex3_1

最新推荐文章于 2022-07-28 18:39:46 发布

slash_hlt

最新推荐文章于 2022-07-28 18:39:46 发布

阅读量1.1k

点赞数

CC 4.0 BY-SA版权

文章标签： machine-learning one

本文链接：https://blog.youkuaiyun.com/slash_HLT/article/details/52167515

本文介绍了一个使用多类逻辑回归的手写数字识别系统实现过程。通过加载和可视化数据集，运用正则化的代价函数进行训练，并最终实现了较高的训练集准确率。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

input_layer_size = 400;

num_labels = 10;

%%Loading and Visualizing Data

load('ex3data1.mat');

m = size(X, 1);

rand_indices = randperm(m);
sel = X(rand_indices(1:100), :);

displayData(sel);

function [h, display_array] = displayData(X, example_width)
if ~exist('example_width', 'var') || isempty(example_width) 
	example_width = round(sqrt(size(X, 2)));
end
colormap(gray);
[m n] = size(X);
example_height = (n / example_width);
display_rows = floor(sqrt(m));
display_cols = ceil(m / display_rows);
pad = 1;
display_array = - ones(pad + display_rows * (example_height + pad), ...
                       pad + display_cols * (example_width + pad));
curr_ex = 1;
for j = 1:display_rows
	for i = 1:display_cols
		if curr_ex > m, 
			break; 
		end
		% Copy the patch
		
		% Get the max value of the patch
		max_val = max(abs(X(curr_ex, :)));
		display_array(pad + (j - 1) * (example_height + pad) + (1:example_height), ...
		              pad + (i - 1) * (example_width + pad) + (1:example_width)) = ...
						reshape(X(curr_ex, :), example_height, example_width) / max_val;
		curr_ex = curr_ex + 1;
	end
	if curr_ex > m, 
		break; 
	end
end
h = imagesc(display_array, [-1 1]);
axis image off
drawnow;
end

%%Vectorize Logistic Regression
lambda = 0.1;
[all_theta] = oneVsAll(X, y, num_labels, lambda);

function [all_theta] = oneVsAll(X, y, num_labels, lambda)
m = size(X, 1);
n = size(X, 2);
all_theta = zeros(num_labels, n + 1);
X = [ones(m, 1) X];
for c = 1:num_labels
    initial_theta = all_theta(c, :)';
    options = optimset('GradObj', 'on', 'MaxIter', 50);
    theta = fmincg (@(t)(lrCostFunction(t, X, (y == c), lambda)), ...
        initial_theta, options);
    all_theta(c,:)=theta';
end
end

%%Predict for One-Vs-All

pred = predictOneVsAll(all_theta, X);

function p = predictOneVsAll(all_theta, X)
m = size(X, 1);
num_labels = size(all_theta, 1);
p = zeros(size(X, 1), 1);
X = [ones(m, 1) X];
[~,p]=max(X*all_theta.',[],2);
end

%% Predict for One-Vs-All
pred = predictOneVsAll(all_theta, X);

fprintf('\nTraining Set Accuracy: %f\n', mean(double(pred == y)) * 100);