AI Engineering 1: Math Foundations

Derive the Linear Algebra Behind Machine Learning

Prerequisite (optional here): The maths courses from the Mathematics, Data Science and Computer Science curricula. This phase puts that maths into code.

3 milestones

1. 1Master Vectors, Matrices, and Linear Transformations
2. 2Apply Linear Algebra to ML Algorithm Derivations
3. 3Present Linear Algebra for ML to an Expert Reviewer

Learn Differentiation (MIT Calculus 1A)

Prerequisite (optional here): The maths courses from the Mathematics, Data Science and Computer Science curricula. This phase puts that maths into code.

2 milestones

1. 1Do the course work in public
2. 2Show a derivative at work in code

Learn Multivariable Calculus (MIT 18.02SC)

Prerequisite (optional here): The maths courses from the Mathematics, Data Science and Computer Science curricula. This phase puts that maths into code.

2 milestones

1. 1Do the course work in public
2. 2Find the best point with gradients

Learn Probability (Harvard Stat 110)

Prerequisite (optional here): The maths courses from the Mathematics, Data Science and Computer Science curricula. This phase puts that maths into code.

2 milestones

1. 1Do the course work in public
2. 2Check a probability puzzle by simulation

Master Statistics for Data Analysis

Prerequisite (optional here): The maths courses from the Mathematics, Data Science and Computer Science curricula. This phase puts that maths into code.

5 milestones

1. 1Describe a real dataset with statistics
2. 2Run and interpret a hypothesis test
3. 3Build and evaluate a regression model
4. 4Design and analyse an A/B test
5. 5Communicate findings to a non-technical audience

Learn Math Foundations (AI Engineering Phase 1)

Phase 1: 22 lessons.

2 milestones

1. 1Do the phase's lessons in public
2. 2Check gradients and do PCA by hand