ML 4: Multiple Features

brandon·2023년 7월 17일
0

SupervisedML

목록 보기
4/27

1. Multivariable Linear Regression

  • vector is just an array.
  • dot product is multiplying by pair.
  • multivariate regression refers to something else.
  • subscript for the specific feature, superscript for specific training data set.

2. Vectorization

  • Making my code deal with vectors instead of multiplying each w by x.
  • Done in NumPy library.



Codewise,

Without Vectorization:

With Vectorization:

Vectorization used in Gradient Descent

  • Just subtract the two vectors.

Multivariable Gradient Descent

Alternative to Gradient Descent

  • using linear algebra to solve for W and B: normal equation.
profile
everything happens for a reason

1개의 댓글

comment-user-thumbnail
2023년 7월 17일

저도 개발자인데 같이 교류 많이 해봐요 ㅎㅎ! 서로 화이팅합시다!

답글 달기