Ridge Regressor

A polynomial regressor which includes an additional regularisation term $λ R (a, b)$ which consists of the sum of the squared values for the trainable parameters

It uses the squared values of the weights: $| | β | |_{2}$

λ R (a, b) = \frac{λ}{2 N} (\sum_{k}^{M} (a_{k})^{2} + b^{2})

Ridge Regressor adds a penalty term proportional to the square of weights.

This tends to shrink weights toward zero (rarely making them exactly zero).

They are represented by the term: $α \sum (w_{j})^{2}$

The regularisation term encourages the model to assign low values to the model parameters, leading to less overfitting.

Also called L2 Regularisation, based on the concept of Lp norms.