#5- Regularization in Logistic Regression equations from scratch(Andrew Ng Coursera Course)
Introduction to Regularization:-00:00
Overfitting and Underfitting:- 1:10
What is Regularization and uses?:- 2:45
Data visualization of Andrew Ng:- 5:10
Why do we need to increase feature? 6:22
Intuition for adding Polynomial feature:- 8:00
Code for Polynomial feature:- 9:20
Code for Cost function:- 21:55
Code for Gradient Descent:- 26:45
Advanced Optimization SciPy:- 33:05
Verification with Sklearn model:-36:15
Intuition for Visualizing Lambda for Regularization:- 36:34
Code for Visualizing Lambda for Regularization:- 40:14
Overfitting when lambda=0:- 47:05
Good fit when lambda=1:- 49:05
Underfitting when lambda=100:- 49:55
Summary:- 50:25
It covers writing #machine #learning #equations for #Regularization in #logistic #regression. It covers intuition, and how regularization aids to avoid #Overfitting in the data. It also includes visualization of #Lambda showing #Overfitting and #Underfitting cases using Andrew Ng #Coursera dataset in #python.(Mathematics of Machine learning)
Github:- https://github.com/akchaudhary57/Mach...
Discussion:- / stepbystepdatascience