Skip to content
AI-grafen
Sign in
☰ Menu

The goal D AI developer

Train your first neural network

Build and train a small neural network in PyTorch, and understand every step: forward pass, loss, gradients and updating the weights.

Knowledge nodes
30
From zero
about 19 h
Labs
6
See what you already know — no account

The diagnostic removes what you already know, so your path is usually much shorter.

What you can do afterwards

Labs along the way

You write the code. Tests you cannot see decide whether it holds up.

Lab: train a digit classifier in PyTorchDa sandbox · about 60 minProject 2: Build a neural network from scratchDa sandbox · about 150 minLab: a neural network in pure NumPy — forward, backprop, gradient checkDa sandbox · about 75 minLab: dot product, norm and cosine similarityDin the browser · about 40 minLab: gradient descent from scratchDin the browser · about 50 minLab: matrix multiplication and one layer of a neural networkDin the browser · about 45 min

The whole path

Everything the goal builds on, grouped by level and in the order it builds on itself. Show on the map

AExplorer2 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
BInvestigator5 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Rule-based systems and machine learning
  4. Training data, features and labels
  5. Classification: how a model sorts information
CBuilder8 knowledge nodes
  1. Functions and coordinate systems
  2. Programming logic — variables, conditions, loops
  3. Python — the basics
  4. Python — lists, loops and dictionaries
  5. Statistics — mean, median and spread
  6. Probability — the basics
  7. Linear regression: fitting a straight line to data
  8. Neural networks — the intuition
DAI developer15 knowledge nodes
  1. Derivatives and optimisation
  2. Python — functions, scope and exceptions
  3. Python — modules, packages and virtual environments
  4. Git — version control
  5. Gradient descent
  6. Precision, recall, F1 and ROC
  7. Vectors
  8. Matrices and matrix multiplication
  9. Neural networks — the forward pass with matrices
  10. Backpropagation
  11. PyTorch — tensors and autograd
  12. Dataloaders, batches and epochs
  13. Train a neural network in PyTorch
  14. MNIST from scratch
  15. Project D: a classifier of your own in PyTorch