机器学习

Different types of Functions

1. Regression: The function outputs a scalar

2. Classification: Given options(classes),the function outputs the correct one

3. Structured Learning

1. Function with Unknown Parameters

Model 在机器学习中就是带有未知的Parameter的function；

w: weight b: bias

2. Define Loss from Training Data

Loss is a function of parameter: $L(b,w)$

Loss: $L=\frac{1}{N}\sum_{i=1}^n{e_n}$ $e_n$为每次误差

$e=|y-\bar{y}|$ L is mean absolute error(MAE) 绝对误差

$e=(y-\bar{y})^2$ L is mean square error(MSE) 平方误差

寻找一个最合适的b和w，使得L最低

3. Optimization

Gradient Descent : 梯度下降

All Piecewise Linear Curves = constant + sum of a set of

sigmod : S型的function