Machine Learning & AI

Intermediate

L2 Regularization (Ridge)

Adds a penalty on squared weights to reduce overfitting.

Formula

J = \text{MSE} + \lambda\sum_j w_j^2

Variables

\lambdaRegularization strength

w_jWeights

Example

Large lambda shrinks all weights toward zero

Did You Know?

L2 shrinks weights smoothly toward zero but rarely makes them exactly zero.

regularization overfitting

Share this formula

More in Machine Learning & AI

Linear Regression Model

Predicts a continuous value as a weighted sum of input features plus a bias.

Gradient Descent Update

Iteratively moves parameters in the direction that most reduces the loss.

ReLU Activation

Rectified Linear Unit: outputs the input if positive, else zero.

Leaky ReLU

A ReLU variant that lets a small gradient flow for negative inputs.

Tanh Activation

Squashes input to the range (-1, 1); zero-centred activation.

Softmax

Turns a vector of scores into a probability distribution that sums to 1.