linear regression: closed-form solution
(1.2 hours to learn)
Summary
Linear regression has a closed-form solution in terms of basic linear algebra operations. This makes it a useful starting point for understanding many other statistical learning algorithms.
Context
This concept has the prerequisites:
- linear regression
- linear least squares (The linear regression parameters are fit by solving a linear least squares problem. The issues involved in linear least squares, such as stability, are important in fitting linear regression as well. Several algorithms for linear least squares have interesting statistical interpretations.)
Core resources (read/watch one of the following)
-Free-
→ Coursera: Machine Learning (2013)
An online machine learning course aimed at a broad audience.
Other notes:
- Click on "Preview" to see the videos.
→ Stanford's Machine Learning lecture notes
Lecture notes for Stanford's machine learning course, aimed at graduate and advanced undergraduate students.
Location:
Chapter 1, section 2, pages 7-11
Supplemental resources (the following are optional, but you may find them useful)
-Paid-
→ Pattern Recognition and Machine Learning
A textbook for a graduate machine learning course, with a focus on Bayesian methods.
Location:
Sections 3.1-3.1.1, pgs. 137-142
→ Pattern Recognition and Machine Learning
A textbook for a graduate machine learning course, with a focus on Bayesian methods.
Location:
Sections 3.1-3.1.1, pgs. 137-142
See also
-No Additional Notes-