Skip to main content
No certificateIntermediateAI & Machine Learning

Practical Deep Learning for Coders

fast.ai's famous top-down deep learning course for people who can already code.

Taught byfast.ai

About this course

Jeremy Howard's course, recorded at the University of Queensland, teaches deep learning by building working models first. Lessons cover deployment, neural net foundations, NLP, models from scratch, random forests, collaborative filtering, CNNs and data ethics, using free notebook platforms.

Best for: Programmers who learn best by building.

What you will be able to do

  • Train and deploy image and text models
  • Understand how neural networks learn
  • Build models from scratch in PyTorch
  • Apply collaborative filtering and random forests

Syllabus and your progress

Tick modules off as you finish them on fast.ai.

0 of 8 modules done

Plan your pace

At 4 hours a week you would finish in about 4 weeks, using the course time estimate above.

Progress is saved in this browser only. No account needed.

Cost and certificate

No certificate

fast.ai does not issue certificates.

Before you start: About a year of coding, ideally Python; High school maths

fast.ai sets the terms and can change them. Check the course page before you commit serious time, and tell us if something changed.

Quick answers

Is Practical Deep Learning for Coders really free?
Yes, the course material is free on fast.ai. fast.ai does not issue certificates.
How long does Practical Deep Learning for Coders take?
Plan for about 14 hrs in total (Nine lessons of about 90 minutes each, per the course page; practice time extra.). It is video lectures, so you can go faster or slower.
Do I need experience before Practical Deep Learning for Coders?
It helps to have: About a year of coding, ideally Python; High school maths.

Part of these learning paths

Featured in

Topics

About fast.ai

Free, practical deep learning courses for coders.

All free fast.ai courses

Practical Deep Learning for Coders

No certificate

Start on fast.ai