Coursera Week 1 - Linear Regression Cost Function & Gradient descent

blairchen

data-science

Publish：Sep 28, 2016

views

Linear Regression Cost Function & Gradient descent

1. Linear Regression

2. Cost Function

Choose $\theta_0，\theta_1$ so that $h_{\theta} (x)$ is close to $y$ for our training examples ${(x, y)}$

3. Simplified Fmt

$\theta_0$ = 0

hypothesis function $h_{\theta} (x)$ cost function $J(\theta_1)$

4. Cost function visable

把 x, y 想象成向量，确定的向量，向量再想象为一个确定的数，总之它是一个二次函数，抽象的想一下，会不会理解

• contour plots
• contour figures

5. Gradient descent target

6. Gradient descent visable

Convex function

7. Gradient descent algorithm

$ \alpha $ : learning rate

8. Gradient descent only $ \theta_{1} $

9. Linear Regression Model

9.1 Batch Gradient Descent

Batch : Each step of gradient descent uses all the training examples

Coursera Learning Notes

updated on：May 2, 2022

machine-learning