2017-11-9

监督学习问题被分为两大类，即回归和分类。

回归与分类的区别：

通俗来讲：

回归模型：用于连续变量预测；分类模型：用于离散变量预测。；区分分类与回归，看的是输出结果的连续与否。

无监督学习问题：（聚类问题）

Unsupervised learning allows us to approach problems with little or no idea what our results should look like. We can derive structure from data where we don't necessarily know the effect of the variables.

We can derive this structure by clustering the data based on relationships among the variables in the data.

With unsupervised learning there is no feedback based on the prediction results.

cost function （代价函数）：squared error cost function （平方误差代价函数）

We can measure the accuracy of our hypothesis function by using a cost function.Gradient Descent(梯度下降)：minimize the cost function

The direction in which the step is taken is determined by the partial derivative ofJ(θ0,θ1). Depending on where one starts on the graph, one could end up at different points.α：learn rate ,decide the length of every step.

the α can not be too small or too largethe α no need change ,becauce deractive is being smaller