All Katas - ML Katas

Working with a NN library: Flax

this year medium (<1 hr) | flax MLP TrainState

While it is possible to build neural networks from scratch in JAX, it is often more convenient to use a library like Flax or Haiku. These libraries provide common neural network layers and...

Checkpointing

this year medium (<30 mins) | flax checkpointing

When training large models, it is important to save the model's parameters periodically. This is known as checkpointing and allows you to resume training from a saved state in case of an...

Build a Simple Neural Network with Flax

this year medium (<30 mins) | mlp jax flax neural-network

Using Flax, JAX's neural network library, build a simple Multi-Layer Perceptron (MLP). The MLP should have an input layer, one hidden layer with a ReLU activation function, and an output layer....