All Katas - ML Katas

by: newest upvotes saves

Numerical Gradient Verification

this year medium (<1 hr) | debugging gradient calculus numerical-stability backpropagation

Understanding and correctly implementing backpropagation is crucial in deep learning. A common way to debug backpropagation is using numerical gradient checking. This involves approximating the...
Differentiating Through a Non-differentiable Function with `torch.autograd.Function`

this year hard (<1 hr) | autograd custom gradient function backprop

Implement a **custom `torch.autograd.Function`** for a non-differentiable operation, such as a custom quantization function. The `forward` method will perform the non-differentiable operation, and...