Skip to content
AI-grafen
Sign in
☰ Menu

The goal E University

Seeing and hearing with AI

Images as matrices, filters that find edges, a trained image classifier, and a model that tells two sounds apart.

Knowledge nodes
32
From zero
about 16 h
Labs
5
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: dot product, norm and cosine similarityDin the browser · about 40 minLab: matrix multiplication and one layer of a neural networkDin the browser · about 45 minLab: mean, median and standard deviation by handCin the browser · about 40 minLab: the best line with least squaresCin the browser · about 40 minProject 1: Teach a computer to recognise patternsCin the browser · about 90 min

The whole path

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

AExplorer6 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
  3. Integer arithmetic and order of operations
  4. What is a computer?
  5. Input and output
  6. Digital images and pixels
BInvestigator7 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Rule-based systems and machine learning
  4. Binary numbers and bits
  5. Training data, features and labels
  6. Classification: how a model sorts information
  7. Sound waves and frequency
CBuilder11 knowledge nodes
  1. Functions and coordinate systems
  2. Statistics — mean, median and spread
  3. Digital representation: text, images and audio
  4. Manual data labelling
  5. Linear regression: fitting a straight line to data
  6. Neural networks — the intuition
  7. Experiment: biased training data and its consequences
  8. Project: train an image classifier in the browser
  9. Filter: identify edges in images
  10. Training a model for audio classification
  11. Images as matrices
DAI developer6 knowledge nodes
  1. Vectors
  2. Matrices and matrix multiplication
  3. Linear regression with several features
  4. Neural networks — the forward pass with matrices
  5. Overfitting and generalisation
  6. Training, validation and test
EUniversity2 knowledge nodes
  1. Convolutional networks (CNNs)
  2. Computer vision — the basics