Practical Deep Learning for Coders
Teaches deep learning by having you train a working model in the first lesson and explaining the theory afterwards, which is the opposite of most curricula and works much better for engineers. Free, and it assumes you can already program.
Course
AI & Machine Learning
fast.ai
8 to 10 weeks
Beginner
Free
The teaching order
Most machine learning courses spend weeks on mathematics before you touch a model. This one trains a useful image classifier in lesson one, then progressively removes the abstractions to explain what happened. For people who already write software, learning by disassembling something that works is far more effective.
What it covers
Computer vision, natural language processing, tabular data and collaborative filtering, then a second half that rebuilds the framework from the foundations so the earlier magic is fully accounted for.
Who it suits
Engineers, not researchers. It is unapologetically practical, prioritising techniques that work over techniques that are elegant, and it is honest about the difference.
A caveat
The material moves quickly and the library it teaches is its own. The concepts transfer everywhere; the specific API does not, and that is a reasonable trade for how fast you get moving.
Best for: working developers who want to add machine learning capability without a year of preparation.
Ready to start?
Opens on fast.ai in a new tab.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Every session is free; a few slots open each week.
Follow along
New writing, resources and project ideas land here first.