Recipe
publicShareStar

Stochastic gradient descent

Collaborators
Reviewers
Total time needed: ~2 hours
Learning Objectives
Learn the basic of stochastic gradient descent as an optimizer
Potential Use Cases
Stochastic Gradient Descent (SGD) is a simple yet very efficient approach to fitting linear classifiers and regressors under convex loss functions
Target Audience
INTERMEDIATE
Go through the following annotated items in order:
VIDEO 1. Stochastic gradient descent
CPSC 340 UBC ML course : lecture on Stochastic Gradient Descent (SGD)
50 minutes
VIDEO 2. Stochastic Gradient Descent
Easy explanation of SGD from Andrew Ng
12 minutes
ARTICLE 3. Toward data science - SGD
easy explanation of SGD
15 minutes
LIBRARY 4. SGD in Scikit-Learn
SGD library in scikit​-learn package in python
10 minutes
VIDEO 5. Gradient Descent with Andrew Ng
easy explanation of gradient descent from Andrew Ng
10 minutes
ARTICLE 6. Stochastic model
explanation of the ​stochastic model
10 minutes

Concepts Covered