Sign in Explore the program

Unlocks after Module 2The AI Engineering Program

Module 3: Mathematics & Statistics for AI

The vectors, derivatives and probability that make machine learning make sense.

33guided hours
15lessons
3 of 13in the program
Enrol in the programTry lesson 1 free
The Lesson 3.8 notes on gradient descent in the learning app

Lessons

15 lessons, in order. Each one unlocks when you finish the one before it.

  1. 3.1
    VectorsLab: ML math notebookAssignment: Implement vector operations in NumPy
  2. 3.2
    Linear combinationsLab: Feature-space visualizerAssignment: Visualize linear combinations
  3. 3.3
    Matrix multiplicationLab: Matrix calculatorAssignment: Implement matrix multiplication manually and with NumPy
  4. 3.4
    Eigenvalues/eigenvectorsLab: PCA intuition labAssignment: Relate eigenvectors to principal directions
  5. 3.5
    DerivativesLab: Gradient intuition labAssignment: Numerically estimate derivatives
  6. 3.6
    Partial derivativesLab: Multivariable gradient labAssignment: Compute partial derivatives for a loss function
  7. 3.7
    Chain ruleLab: Backprop precursorAssignment: Trace derivatives through a two-layer function
  8. 3.8
    Gradient descentLab: Optimizer visualizerAssignment: Implement gradient descent from scratch
  9. 3.9
    Probability fundamentalsLab: Probability simulatorAssignment: Simulate Bernoulli/binomial events
  10. 3.10
    Conditional probability/BayesLab: Bayes classifier labAssignment: Implement a simple Bayesian classifier
  11. 3.11
    Expectation and varianceLab: Distribution analysisAssignment: Compute expectation/variance from data
  12. 3.12
    Correlation vs causationLab: Analytics critiqueAssignment: Identify misleading correlations
  13. 3.13
    Sampling and confidence intervalsLab: Experiment analysisAssignment: Build confidence intervals from samples
  14. 3.14
    Hypothesis testingLab: A/B test analysisAssignment: Test a marketing/product hypothesis
  15. 3.15
    Math-to-ML checkpointLab: ML math diagnosticAssignment: Explain where each math concept enters an ML pipeline

Module project

Math-to-ML notebook. A model trained by hand in NumPy, every step explained.

It goes in your portfolio, with a README a recruiter can read in a minute.

PreviousModule 2: Python for AINextModule 4: Data, SQL & Machine Learning in Practice

See all 13 modules

Your first lesson is on us.

AI vs ML vs DL vs GenAI: deep notes, a hands-on lab and a quiz. No card. No catch.

Start lesson 1 free