All Katas - ML Katas

Implementing a Siamese Network with Triplet Loss

this month hard (>1 hr) | siamese loss learning triplet metric

Building on the previous exercise, let's switch to **Triplet Loss**. This loss function is more powerful as it enforces a margin between an anchor-positive pair and an anchor-negative pair. The...

Implementing a Custom Loss Function with `torch.autograd`

this month medium (<30 mins) | regression loss custom function huber

Create a **custom loss function** that inherits from `torch.nn.Module` and performs a non-standard calculation. For example, a custom Huber loss. This loss is less sensitive to outliers than Mean...

Neural Style Transfer

this month hard (>1 hr) | style transfer vgg loss image

Implement **Neural Style Transfer**. Given a content image and a style image, generate a new image that combines the content of the former with the style of the latter. Use a pre-trained VGG...

Training a Variational Autoencoder (VAE)

this month hard (>1 hr) | loss vae autoencoder generative kl

Implement and train a **Variational Autoencoder (VAE)** on a dataset like MNIST. The encoder should map the input to a latent space distribution (mean and variance), and the decoder should...