All Katas - ML Katas

by: newest upvotes saves

Taking gradients with `grad`

this year easy (<30 mins) | grad autodiff

One of JAX's most powerful features is its ability to automatically differentiate your code. In this exercise, you will implement a regression problem and use `jax.grad` to compute gradients. 1....
Taking gradients with `grad` II

this year easy (<10 mins) | grad autodiff

By default, `jax.grad` will take the gradient with respect to the first argument of the function. However, in many cases, we will want to take gradients with respect to many of the function's...