Diagnosing Regularization Bias vs. Variance

Diagnosing Bias vs. Variance

This means:

• High bias = under-fitting = \(J_{train}(\theta)\) high and \(J_{cv}(\theta)\) high
• High variance = over-fitting = \(J_{train}(\theta)\) low and \(J_{cv}(\theta)\) high

Regularization: help prevent overfitting

This is the next step once we chose the degree of polynomial for our dataset

This means: 

• Large \(\lambda\) = High bias = \(J_{train}(\theta)\) high and \(J_{cv}(\theta)\) high
• Small \(\lambda\) = High variance = \(J_{train}(\theta)\) low and \(J_{cv}(\theta)\) high

Steps:

Resources:

- https://www.coursera.org/learn/machine-learning/supplement/81vp0/diagnosing-bias-vs-variance

- https://www.coursera.org/learn/machine-learning/supplement/JPJJj/regularization-and-bias-variance