ML(머신러닝) :: Linear Regression with Multiple features

Contents in the post based on the free Coursera Machine Learning course, taught by Andrew Ng.

From now on we are going to learn about the new version of Linear Regression which is more powerful.

1. Multivariate Linear Regression

1.1 Previously :: Linear regression with one variable (Univariate Linear regression)

1.2 Multiple features (variables)

1.3 Vectorization

Vectorization

For convenience, by setting x0 = 1, we can utilize the vectorization.

2. Cost Function for Multiple Variables

3. Gradient Descent for Multiple Variables

3.1 Previously :: Linear regression with one variable (Univariate Linear regression)

- n = 1

You need to simultaneously update θ0, θ1

3.2 Multiple features (variables)

- n >= 1

For now, You need to update θj (j = 0, ... , n) simultaneously.