梯度下降算法到logistic回归

http://sbp810050504.blog.51cto.com/2799422/1608064/

http://blog.csdn.net/dongtingzhizi/article/details/15962797

http://blog.csdn.net/llp1992/article/details/45114421

https://www.qcloud.com/community/article/180954?fromSource=gwzcw.107192.107192.107192

梯度上升法求函数极值

来源: 运筹学第3版 胡运权 第3 节无约束极值问题的解法

logistic回归进行二分类

function weight = gradAscent
clc
% close all
clear
%%

data = load('testSet.txt');
[row , col] = size(data);
dataMat = data(:,:col-);
dataMat = [ones(row,) dataMat] ;
labelMat = data(:,col);
alpha = 0.001;
maxCycle = ;
weight = ones(col,);
for i = :maxCycle
    h = sigmoid(dataMat * weight);
    error = (labelMat - h);
    weight = weight + alpha * dataMat' * error;
end

figure
scatter(dataMat(find(labelMat(:) == ),),dataMat(find(labelMat(:) == ),),);
hold on
scatter(dataMat(find(labelMat(:) == ),),dataMat(find(labelMat(:) == ),),);
hold on
x = -:0.1:;
y = (-weight()-weight()*x)/weight();
plot(x,y)
hold off

end

function returnVals = sigmoid(inX)
    returnVals = 1.0./(1.0+exp(-inX));
end