SVM vs. logistic regression
(35 minutes to learn)
Summary
Logistic regression and SVMs are closely related algorithms, even though this isn't obvious from the usual presentation. In particular, the loss functions are very similar, and linear SVMs and logistic regression can often be substituted for one another without a big difference in performance.
Context
This concept has the prerequisites:
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.
→ The Elements of Statistical Learning
A graudate-level statistical learning textbook with a focus on frequentist methods.
-Paid-
→ Pattern Recognition and Machine Learning
A textbook for a graduate machine learning course, with a focus on Bayesian methods.
Location:
Section 7.1.2, pages 336-338
See also
-No Additional Notes-