← All 186 courses
AI-103 AI & Data

Mathematics & Statistics for Machine Learning

Demystify the mathematics that ML rests on — linear algebra, calculus, probability and statistics — taught visually and computationally rather than by proof. Learners connect each concept directly to where it appears inside a model, from gradients in backpropagation to distributions in evaluation.

B2Foundation
5modules
34skill atoms
2role journeys
Curriculum

What this course covers.

5 modules, 34 named skill atoms. Expand any module to see them.

1Linear Algebra for ML7 skill atoms
vectors & matricesdot productsembeddings intuitionmatrix shapes & broadcastingnorms & distancecosine similarityeigenvector intuition
2Calculus of Learning7 skill atoms
derivativesgradientswhy loss curves movechain rulepartial derivativeslearning-rate effectslocal minima & saddle points
3Probability Essentials7 skill atoms
distributionsconditional probabilityBayes intuitionnormal & Bernoulliexpectation & varianceindependencelikelihood vs probability
4Statistics for Evaluation7 skill atoms
samplingconfidencesignificance trapscentral limit theoremconfidence intervalsp-value misuseeffect size
5Applied Notebook Lab6 skill atoms
implement gradient descent by handverify vs libraryNumPy vectorizationconvergence plotslearning-rate sweepnumerical gradient check
Where it fits

AI-103 in the role journeys.

This course appears in 2 of our 45 role journeys. Here is what a learner takes immediately before and after it in each.

AI / ML Engineer

Foundation stage
AI-102AI-103AI-104

Data Scientist

Foundation stage
AI-102AI-103AI-104

Roles this course serves

The capability ladder

This course is authored to band B2.

Every course we run is written to one rung of the CASI ladder, so a plan can be assembled to take a team from where they are to where they need to be.

What do B1–B6 mean?The CASI Capability Ladder — click to expand

Every course targets a band on the CASI Capability Ladder — our six-band proficiency scale, anchored to open standards (O*NET, ESCO, NICE, NIST AI RMF, Bloom's). A band tells you how deep a course goes, and what evidence proves it.

What the learner can doTypical evidence
B1
AwareUnderstands concepts and vocabulary; uses tools with guidance
Knowledge checks
B2
FoundationPerforms standard tasks correctly in familiar contexts
Guided labs, autograded exercises
B3
PractitionerDelivers complete pieces of work independently
Scenario labs, proctored hands-on exams
B4
ProfessionalHandles production-grade complexity, trade-offs and failure modes
Break-fix drills, design defenses
B5
AdvancedEngineers systems end-to-end under constraints; leads others
Rubric-scored capstones, vivas
B6
ExpertSets direction; recognised authority across teams
Portfolio + panel evaluation

A note on B6. Courses in this catalog target B1–B5. B6 is not taught — it is recognised, through a portfolio and a panel, once someone is setting direction for others. Every journey here is built to land a learner at B5.

Next step

Run AI-103 for your team.

This course runs at several lengths depending on how deep you need to go and how much of it your people already have. Tell us who is being trained and we will scope it.

Add it to a training plan Talk to our team Check your team’s level free