Skip to content

Career path

AI from Scratch

Implement the math behind modern ML — backprop in a neural network, then a GPT-style transformer. No PyTorch shortcuts.

advanced2 courses39 lessons~10 hoursFree
Start pathor sign up to track progress

Start → ship

1

You start with

Build a Neural Network

2

You ship

Build a Transformer (GPT-style)

2 courses in order, every exercise graded on the executor.

Course sequence

Follow it in order. Each course is its own certificate.

  1. 1

    Build a Neural Network

    Not started

    Build an MNIST classifier from scratch in NumPy: neurons, dense layers, sigmoid/ReLU/softmax, MSE/cross-entropy loss, manual backpropagation, gradient descent + Adam, training loop, and the path to PyTorch/TensorFlow.

    advanced25 lessons~6h
  2. 2

    Build a Transformer (GPT-style)

    Not started

    Build a tiny GPT in NumPy: token + position embeddings, layer normalization, scaled dot-product self-attention, multi-head attention with causal mask, feed-forward networks, residual connections, sampling (greedy, top-k, top-p), and the architecture behind ChatGPT, Claude, Llama.

    advanced14 lessons~4h

Create a free account to track your progress across this path.