All Katas - ML Katas

L2 Regularization Gradient

this year easy (<10 mins) | regularization gradient linear-regression calculus overfitting

L2 regularization (also known as Ridge Regression or weight decay) is a common technique to prevent overfitting in machine learning models by adding a penalty proportional to the square of the...

Linear Regression via Gradient Descent

this year medium (<1 hr) | optimization linear-regression calculus gradient-descent machine-learning

Linear regression is a foundational supervised learning algorithm. Given a dataset of input features $X$ and corresponding target values $y$, the goal is to find a linear relationship $y =...

Implement a Simple Linear Regression in JAX

this year easy (<30 mins) | autograd optimization jax jit linear-regression

Your task is to implement a simple linear regression model from scratch using JAX. You'll need to define the model, a loss function (like Mean Squared Error), and a gradient descent update rule....