All Katas - ML Katas

Tensor Manipulation: Creating `unfold` with `as_strided`

today hard (<10 mins) | pytorch tensor advanced

### Description **Warning: `as_strided` is an advanced and potentially unsafe operation that can crash your program if used incorrectly, as it creates a view on memory without checks.** With that...

Implement a Neural Ordinary Differential Equation

this week hard (<30 mins) | pytorch generative neural ode dynamics

### Description Instead of modeling a function directly, a Neural ODE models its derivative with a neural network. The output is then found by integrating this derivative over time. [1] Your task...

Model-Agnostic Meta-Learning (MAML) Update Step

this week hard (<30 mins) | pytorch meta-learning maml few-shot

### Description Model-Agnostic Meta-Learning (MAML) is a meta-learning algorithm that trains a model's initial parameters such that it can adapt to a new task with only a few gradient steps. [1]...

Build a Transformer Encoder Block from Scratch

this week hard (<30 mins) | pytorch transformer attention nlp

### Description The Transformer architecture is built upon a fundamental component: the Encoder block. [1] Each block is responsible for processing a sequence of embeddings and refining them. Your...

Soft Actor-Critic (SAC) Critic Loss

this week hard (<30 mins) | pytorch reinforcement rl sac actor-critic

### Description Soft Actor-Critic (SAC) is a state-of-the-art reinforcement learning algorithm known for its stability and sample efficiency. [1] A key component is its critic (or Q-network)...

Neural Cellular Automata (NCA) Update Step

this week hard (<30 mins) | pytorch generative nca alife complex systems

### Description Neural Cellular Automata (NCA) are a fascinating generative model where complex global patterns emerge from simple, local rules learned by a neural network. [1] A grid of "cells,"...

Bayesian Neural Network Layer

this week hard (<30 mins) | pytorch bayesian bnn uncertainty

### Description In a standard neural network, weights are single point estimates. In a Bayesian Neural Network (BNN), we learn a probability distribution over each weight. [1] This allows for...

Siamese Network for One-Shot Image Verification

this week hard (<30 mins) | pytorch siamese metric learning one-shot

### Description Your task is to implement a Siamese network that can determine if two images are of the same class, given only one or a few examples of that class at test time. You'll train a...

Physics-Informed Neural Network (PINN) for an ODE

this week hard (<30 mins) | pytorch autograd ode pinn physics

### Description Solve a simple Ordinary Differential Equation (ODE) using a Physics-Informed Neural Network. A PINN is a neural network that is trained to satisfy both the data and the underlying...

Graph Convolutional Network for Node Classification

this week hard (<30 mins) | pytorch gnn graph gcn

### Description Implement a simple Graph Convolutional Network (GCN) to perform node classification on a graph dataset like Cora. [1] A GCN layer aggregates information from a node's neighbors to...

HyperNetwork for Weight Generation

this week hard (<30 mins) | pytorch hypernetwork meta-learning

### Description Implement a simple HyperNetwork. A HyperNetwork is a neural network that generates the weights for another, larger network (the "target network"). [1] This allows for dynamic...

Normalizing Flow for Density Estimation

this week hard (<30 mins) | pytorch generative normalizing flow

### Description Implement a simple 2D Normalizing Flow model. Normalizing Flows transform a simple base distribution (like a Gaussian) into a more complex distribution by applying a sequence of...

Spiking Neuron with Leaky Integrate-and-Fire

this week hard (<30 mins) | pytorch snn spiking neuroscience

### Description Implement a single Leaky Integrate-and-Fire (LIF) neuron, the fundamental building block of many Spiking Neural Networks (SNNs). Unlike traditional neurons, LIF neurons operate on...