Skip to content
AI-grafen
Sign in
☰ Menu

The goal E University

Classical ML for real

Margins, outliers, recommendations and systematic hyperparameter search — the methods that still solve most problems more cheaply than a neural network.

Knowledge nodes
64
From zero
about 47 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: 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: k-means from scratchDa sandbox · about 45 minLab: k-nearest neighbours from scratchDa sandbox · about 45 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

AExplorer3 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
  3. Integer arithmetic and order of operations
BInvestigator7 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Rule-based systems and machine learning
  4. Fractions, decimals, and percentages
  5. Negative numbers in everyday life and AI
  6. Training data, features and labels
  7. Classification: how a model sorts information
CBuilder12 knowledge nodes
  1. Functions and coordinate systems
  2. Programming logic — variables, conditions, loops
  3. Python — the basics
  4. Python — lists, loops and dictionaries
  5. Python — strings and text processing
  6. Python — files, CSV and JSON
  7. Statistics — mean, median and spread
  8. Probability — the basics
  9. Linear regression: fitting a straight line to data
  10. Neural networks — the intuition
  11. Variables and algebraic expressions
  12. Powers and roots
DAI developer23 knowledge nodes
  1. Discrete mathematics: graphs and relations
  2. Derivatives and optimisation
  3. Time complexity and big-O notation
  4. Data structures: lists, stacks, queues, hash tables
  5. Conditional probability
  6. Bayes' theorem
  7. Probability distributions
  8. Gradient descent
  9. Logarithms
  10. Vectors
  11. Clustering: k-means and hierarchical
  12. k-nearest neighbours (kNN)
  13. Matrices and matrix multiplication
  14. Linear regression with several features
  15. Logistic regression and decision trees
  16. Decision trees
  17. Neural networks — the forward pass with matrices
  18. Backpropagation
  19. NumPy — arrays and vectorisation
  20. Overfitting and generalisation
  21. Pandas — tables in Python
  22. Training, validation and test
  23. Cross-validation
EUniversity17 knowledge nodes
  1. Convexity and the optimisation landscape
  2. Graph algorithms: BFS, DFS, topological order
  3. Maximum likelihood
  4. Anomaly detection
  5. Ensembles: random forest and boosting
  6. Linear maps
  7. Eigenvalues and eigenvectors
  8. Matrix factorisation and low-rank approximation
  9. Recommender systems
  10. Sequence models before transformers
  11. Singular value decomposition (SVD)
  12. PCA — principal component analysis
  13. Dimensionality reduction: PCA, t-SNE, UMAP
  14. Support vector machines (SVM)
  15. Time series
  16. Sequence models for time series
  17. Hyperparameter search
FAI engineering2 knowledge nodes
  1. Bayesian inference
  2. Graph neural networks (GNNs)