Python cheatsheet
Every syntax pattern from subject 01 on four sides of paper, with the error messages you will actually hit and what they mean.
PDFComing soon
Resources
Free guides, books, research papers, tools and downloadable material. Take any of it, use it, teach from it.
Free guides
Written to be printed
Short, dense PDFs that work on paper and offline — for classrooms without reliable electricity as much as for revision. Each one is published alongside the subject it belongs to.
Machine learning glossary
Two hundred terms defined once, properly, in plain English. Print it and keep it beside you.
PDFComing soon
Prompting patterns card
The five patterns from subject 07, with a worked example of each and the failure each one prevents.
PDFComing soon
Mathematics you actually need
The linear algebra, calculus and probability required for subjects 03 and 04 — and an explicit list of what you can skip.
PDFComing soon
Teacher's pack
Lesson plans, discussion questions and a marking guide, for teaching any subject in a classroom with no internet.
PDFComing soon
Portfolio checklist
What a hiring manager looks for in a GitHub project, and the six things that make yours look unfinished.
PDFComing soon
Guides are published as each subject is finished. All are licensed Creative Commons BY-SA: translate them, print them, sell the printing — just keep the attribution and the same licence.
Books and research papers
Every book here is legally free
You do not need to buy anything to learn this properly. These are the standard texts, published free by their authors, plus the papers worth reading in the original.
Books
- MATHMathematics for Machine LearningDeisenroth, Faisal & Ong — start here if the mathematics is the barrier
- MLAn Introduction to Statistical LearningJames, Witten, Hastie & Tibshirani — the friendliest serious ML book
- MLThe Elements of Statistical LearningHastie, Tibshirani & Friedman — the harder companion to the above
- DLDeep LearningGoodfellow, Bengio & Courville — the reference text
- DLDive into Deep LearningZhang et al. — every concept with runnable code beside it
- NLPSpeech and Language ProcessingJurafsky & Martin — the language processing standard, draft chapters free
Papers
- 2017Attention Is All You NeedVaswani et al. — the transformer. Read it after subject 04, not before
- 2018BERTDevlin et al. — pre-training that made transfer learning normal in NLP
- 2020Language Models are Few-Shot LearnersBrown et al. — where prompting as a technique comes from
- 2020Retrieval-Augmented GenerationLewis et al. — the paper behind subject 07
- 2022ReAct: Synergizing Reasoning and ActingYao et al. — the loop at the centre of subject 08
- 2018Model Cards for Model ReportingMitchell et al. — how to document what a model does and to whom