Machine Learning

What the course covers

9 lectures, 6 hours

• Introduction to ML: supervised versus unsupervised learning, train/test split
• Linear Regression and the cost function
• Gradient Descent
• Regression metrics such as MSE and R²
• Logistic Regression and the sigmoid function
• Classification metrics: accuracy, precision, recall and the confusion matrix
• Decision Trees with entropy and Gini
• Tree ensembles such as Random Forest
• Implementing the models in Python on real data

What you will be able to do

• Derive the cost function for linear and logistic regression and run Gradient Descent steps by hand on a small example.
• Compute evaluation metrics from a confusion matrix and interpret a model's results.
• Build a decision tree on tabular data by computing entropy and information gain for each split.
• Train regression and classification models in Python and compare their performance.

Free lectures from this course

Complete lectures from inside the courses, with no sign-up and no limits, so you know the style and depth before paying a single riyal.

In teaching order. All of them open to you on enrollment until the end of the semester.

1. 1Introduction46 min
2. 2Linear Regression, part 134 min
3. 3Linear Regression, part 242 min
4. 4Logistic Regression, part 120 min
5. 5Logistic Regression, part 238 min
6. 6Logistic Regression, part 332 min
7. 7Tree Methods, part 156 min
8. 8Tree Methods, part 222 min
9. 9Tree Methods, part 351 min

Prerequisites

• Python basics
• Basic linear algebra and statistics

About this course