aka regression

Discriminative Supervised learning where the output value is continuous, and quantiative (i.e. it has an ordering, and a notion of closeness (matrix)).

Notes

Linear regression

• Nonparametric version: Locally-weighted linear regression
• Ridge regression
• Lasso

Nearest-neighbour classification

Kernel linear regression

Nonlinear regression

• Deep learning

Multiclass MLP

Regularizer helps control the model complexity (by constrianing the size of the parameter vector $\mathbf{\theta}$). It can also be seen as adding a prior (in Bayesian statistics)

https://www.wikiwand.com/en/Regression_analysis