Module 1ConceptsNumbers, notation and data summaries
3 lessonsRead the symbols in a formula, then describe a set of numbers with the right summary. You see why one large value moves the mean but not the median, and how a chart can mislead.
Essential Mathematics and Statistics for AI
The mathematics and statistics behind AI, shown with real examples and charts you can change. You learn what the numbers mean and how to use them in decisions, not how to calculate by hand.
- 18 lessons
- 12–16 hr
- Beginner
- Check in every lesson
- Free certificate
Read every lesson as a guest, or sign in to enroll and track your progress.
Enroll to save the lessons that you complete. It is free.
What you'll learn
By the end of this course, you will be able to:
- Interpret vectors, matrices and similarity.
- Explain probability and uncertainty using concrete examples.
- Connect derivatives and gradients to learning.
- Choose sensible statistical summaries and comparisons.
About this course
AI systems are built from numbers. A model stores a customer message as a list of numbers. It learns by making one number, the loss, smaller. A team decides to release it because a test result is good enough. If you can read these numbers, you can follow the work, ask the right questions and see a weak claim before it causes harm.
This course teaches the mathematics and statistics that AI work uses every day, from the practical side. You do not prove theorems or calculate long formulas by hand. Instead, every idea starts with a real situation: a support team at a fictional online shop, Larkfield, that uses AI to sort its customer tickets. You see each idea in a chart, change it in an interactive explorer, and then use it to make a decision.
At the end, you write an illustrated reasoning workbook for a small prediction problem: the summaries, the similarity, the probabilities, a few training steps, the uncertainty and a threshold recommendation, each with a chart and an honest explanation. You need a browser and a calculator.
Before you start
None. You need a browser and a calculator (a phone calculator is enough). Some lessons have optional Python boxes that run in the browser; every one of them has a version without code.
Who this is for
Fresh graduates and professionals who want to work with AI and need to read its numbers with confidence. This includes people who have not used mathematics since school.
Lead or use AI, but do not build it?
You can study the ideas of this course without writing code. Read modules 1, 3, 5 and 6 (about 5–6 hours), answer their knowledge checks, and get a free concepts certificate. You can come back for the practice later.
- Module 1 Numbers, notation and data summaries
- Module 3 Probability and conditional reasoning
- Module 5 Sampling and statistical evidence
- Module 6 Statistics for model decisions
The paths for people who lead or use AI take this course this way. See the paths
How we made this course
Experienced AI practitioners designed this course. AI helped us draft the content; people chose the teaching approach and the examples, and reviewed every lesson. The outputs that you see are the actual results of running the code. How we make our courses
Inside the course
Module 2Vectors and matrices
3 lessonsSee how an AI system stores a ticket, a photo or a sentence as a list of numbers. You use vectors to find similar items, the idea behind search and recommendations.
Module 3ConceptsProbability and conditional reasoning
3 lessonsReason about chance with counts, not formulas. You find out why most alerts for a rare problem are false alarms, and which distributions describe the data that you see.
Module 4How models learn
3 lessonsWatch a model learn. You follow a loss curve downhill one step at a time, and see why a learning rate that is too small or too large makes training fail.
Module 5ConceptsSampling and statistical evidence
3 lessonsDecide what a test result really shows. You measure how much a result can change by chance, and you check if a small improvement is real before you claim it.
Module 6ConceptsStatistics for model decisions
3 lessonsTurn model scores into decisions. You move a threshold and watch precision, recall and cost change, then check if the scores can be trusted for every group.
After Module 6Final assignment
Use every module in one practice project. You collect evidence, and check it against the course outcomes.
- Final assignment150 min
Learn more from the community
Other people teach this subject well too. We chose these to go with this course. They open on other sites.See all community picks
ChannelYouTube · Grant Sanderson
3Blue1Brown (opens in a new tab)
Why we recommend itGrant Sanderson makes hard mathematics easy to see. Start with his series on neural networks and on linear algebra. They are a very good partner to our mathematics course.
ChannelYouTube · Luis Serrano
Luis Serrano Academy (opens in a new tab)
Why we recommend itLuis Serrano explains machine learning, the mathematics behind it and how transformers work, with simple pictures and friendly examples. He is the author of Grokking Machine Learning. A good partner to our mathematics and machine learning courses.
Reviews
Loading the reviews…
Took this course? Sign in to review it. Learners can write a review after they complete 25% of the lessons.