Learn how to

• Measure model performance using loss functions
• Use loss functions as the basis for gradient descent
• Optimize gradient descent to be as efficient as possible
• Use performance metrics to make business decisions

Defining ML Models

Mathematical functions with parameters and hyper-parameters

• Parameter - real-valued variable that changes during model training
• Hyper-parameter - setting that we set before training and doesn't change afterwards

Summary
Measure model performance using loss functions
Use loss functions as the basis for gradient descent