Module 01
Mathematics for Machine Learning
You already did most of this in your ECE degree. This module reframes it around the three questions ML keeps asking: what shape is the data, which way is downhill, and how sure am I.
24 topics ~116 h estimated learning time
Sign in to keep your progress.
Ready to start
- 1.1 Vectors, spaces and geometric intuition
Foundation · 6 h
- 1.2 Matrices as linear maps
Foundation · 6 h
- 1.3 Systems, rank, inverse, determinant
Foundation · 5 h
- 1.4 Eigenvalues and eigenvectors
Core · 6 h
- 1.5 SVD and low-rank approximation
Core · 6 h
- 1.6 Norms, projections and least squares
Core · 5 h
- 1.7 Derivatives, gradients, Jacobians, Hessians
Foundation · 6 h
- 1.8 Chain rule and computational graphs
Core · 4 h
- 1.9 Convexity and the shape of loss surfaces
Core · 4 h
- 1.10 Gradient descent and its variants
Core · 6 h
- 1.11 Constrained optimization
Advanced · 4 h
- 1.12 Probability foundations and Bayes
Foundation · 5 h
- 1.13 Random variables and distributions
Foundation · 6 h
- 1.14 Expectation, variance and moments
Foundation · 4 h
- 1.15 Joint, marginal and conditional distributions
Core · 4 h
- 1.16 Law of large numbers and the CLT
Core · 3 h
- 1.17 Maximum likelihood and MAP
Core · 5 h
- 1.18 Information theory essentials
Core · 4 h
- 1.19 Descriptive statistics and distribution shape
Foundation · 3 h
- 1.20 Sampling, standard error and confidence intervals
Core · 5 h
- 1.21 Hypothesis testing and p-values
Core · 5 h
- 1.22 A/B testing and experiment design
Core · 5 h
- 1.23 Correlation, causation and confounding
Core · 4 h
- 1.24 Bayesian inference in practice
Advanced · 5 h