Stage 2 of 7 · 9 lessons · ~3 months
The maths you need
The linear algebra, calculus, probability and statistics that show up in every model and every evaluation. Aimed at intuition and working in code, not proofs.
Start: Vectors, matrices and the dot productLessons· one lesson for each topic, in this order
- 1Vectors, matrices and the dot productLesson
- 2Matrix multiplication and shapesLesson
- 3Derivatives and gradientsLesson
- 4The chain ruleLesson
- 5Gradient descentLesson
- 6Probability and Bayes' theoremLesson
- 7Probability distributionsLesson
- 8Descriptive statisticsLesson
- 9Hypothesis tests, p-values and confidence intervalsLesson
Start with· follow one of these
- CoursePaidMathematics for Machine Learning and Data Science Specialization
DeepLearning.AI · Beginner · Coursera subscription; financial aid available
Paid, with financial aid: linear algebra, calculus and statistics taught visually with Python labs
- CourseFreeKhan Academy Statistics and Probability
Khan Academy · Beginner
Free, complete statistics and probability with practice questions on every topic
Keep handy
Also worth your time
- Mathematics for Machine LearningGo deeper
Free book that ties the maths directly to regression, PCA and classifiers
Before moving on: Implement linear regression with gradient descent in NumPy from scratch, and explain in plain words what a p-value and a confidence interval do and do not tell you.
Statistics will save you from more bad conclusions than calculus ever will, so do not skip it. Learn each idea alongside NumPy code rather than on paper alone, and do not wait to finish this stage before starting classical ML: run them side by side.