What it is
Practical Deep Learning for Coders is a free, self-paced deep learning course published at course.fast.ai by the non-profit research group fast.ai, co-founded by Jeremy Howard and Rachel Thomas in October 2016 (Wikipedia). Jeremy Howard, a former President and Chief Scientist of Kaggle, leads the course.
What you learn
The course teaches how to build and deploy deep learning models using PyTorch and the fastai library, covering computer vision, natural language processing, tabular data and collaborative filtering. Each video lesson is paired with a runnable Jupyter notebook that can be worked through on free-tier Kaggle Notebooks or Paperspace Gradient, so no local GPU is required.
Format and time commitment
Part 1 has 9 lessons of around 90 minutes each, according to the course page; a further Part 2 covering more advanced material is also published. There is no fixed schedule — learners start whenever they like by opening Lesson 1 directly on the site.
Prerequisites
The course page states the only prerequisite is "a year" of coding experience, preferably in Python, plus a high-school-level maths course. No prior machine learning background is assumed.
Price
The course is free, with no signup required to start watching. A free companion book and community forums are also linked from the course page.
