https://www.coursera.org/learn/machine-learning/home/week/1

## 介绍

A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.

## 梯度下降

setup：

• cost function: $J(\theta_0,\theta_1)$
• want : $\arg\min_{\theta_0,\theta_1}J(\theta_0,\theta_1)$

outline：

• start with some $\theta_0,\theta_1$
• Keep changing $\theta_0,\theta_1$ to reduce $J(\theta_0,\theta_1)$ until we hopefully end up at a minimum.

for j = (0,1)

### Learning rate

$\alpha$ 被称为学习速率，如果 $\alpha$ 太小则学习速度慢(收敛慢)，如果$\alpha$太大，则也有可能无法收敛

- - - - - - - - End Thank For Your Reading - - - - - - - -
0%